CINXE.COM

<!DOCTYPE html> <html lang="en" xmlns:fb="http://www.facebook.com/2008/fbml" class="wf-loading"> <head prefix="og: https://ogp.me/ns# fb: https://ogp.me/ns/fb# academia: https://ogp.me/ns/fb/academia#"> <meta charset="utf-8"> <meta name=viewport content="width=device-width, initial-scale=1"> <meta rel="search" type="application/opensearchdescription+xml" href="/open_search.xml" title="Academia.edu"> <title>Changki Lee | Kangwon National University - Academia.edu</title>  <link href="//a.academia-assets.com/images/favicons/favicon-production.ico" rel="shortcut icon" type="image/vnd.microsoft.icon"> <link rel="apple-touch-icon" sizes="57x57" href="//a.academia-assets.com/images/favicons/apple-touch-icon-57x57.png"> <link rel="apple-touch-icon" sizes="60x60" href="//a.academia-assets.com/images/favicons/apple-touch-icon-60x60.png"> <link rel="apple-touch-icon" sizes="72x72" href="//a.academia-assets.com/images/favicons/apple-touch-icon-72x72.png"> <link rel="apple-touch-icon" sizes="76x76" href="//a.academia-assets.com/images/favicons/apple-touch-icon-76x76.png"> <link rel="apple-touch-icon" sizes="114x114" href="//a.academia-assets.com/images/favicons/apple-touch-icon-114x114.png"> <link rel="apple-touch-icon" sizes="120x120" href="//a.academia-assets.com/images/favicons/apple-touch-icon-120x120.png"> <link rel="apple-touch-icon" sizes="144x144" href="//a.academia-assets.com/images/favicons/apple-touch-icon-144x144.png"> <link rel="apple-touch-icon" sizes="152x152" href="//a.academia-assets.com/images/favicons/apple-touch-icon-152x152.png"> <link rel="apple-touch-icon" sizes="180x180" href="//a.academia-assets.com/images/favicons/apple-touch-icon-180x180.png"> <link rel="icon" type="image/png" href="//a.academia-assets.com/images/favicons/favicon-32x32.png" sizes="32x32"> <link rel="icon" type="image/png" href="//a.academia-assets.com/images/favicons/favicon-194x194.png" sizes="194x194"> <link rel="icon" type="image/png" href="//a.academia-assets.com/images/favicons/favicon-96x96.png" sizes="96x96"> <link rel="icon" type="image/png" href="//a.academia-assets.com/images/favicons/android-chrome-192x192.png" sizes="192x192"> <link rel="icon" type="image/png" href="//a.academia-assets.com/images/favicons/favicon-16x16.png" sizes="16x16"> <link rel="manifest" href="//a.academia-assets.com/images/favicons/manifest.json"> <meta name="msapplication-TileColor" content="#2b5797"> <meta name="msapplication-TileImage" content="//a.academia-assets.com/images/favicons/mstile-144x144.png"> <meta name="theme-color" content="#ffffff"> <script> window.performance && window.performance.measure && window.performance.measure("Time To First Byte", "requestStart", "responseStart"); </script> <script> (function() { if (!window.URLSearchParams || !window.history || !window.history.replaceState) { return; } var searchParams = new URLSearchParams(window.location.search); var paramsToDelete = [ 'fs', 'sm', 'swp', 'iid', 'nbs', 'rcc', // related content category 'rcpos', // related content carousel position 'rcpg', // related carousel page 'rchid', // related content hit id 'f_ri', // research interest id, for SEO tracking 'f_fri', // featured research interest, for SEO tracking (param key without value) 'f_rid', // from research interest directory for SEO tracking 'f_loswp', // from research interest pills on LOSWP sidebar for SEO tracking 'rhid', // referrring hit id ]; if (paramsToDelete.every((key) => searchParams.get(key) === null)) { return; } paramsToDelete.forEach((key) => { searchParams.delete(key); }); var cleanUrl = new URL(window.location.href); cleanUrl.search = searchParams.toString(); history.replaceState({}, document.title, cleanUrl); })(); </script> <script async src="https://www.googletagmanager.com/gtag/js?id=G-5VKX33P2DS"></script> <script> window.dataLayer = window.dataLayer || []; function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); gtag('config', 'G-5VKX33P2DS', { cookie_domain: 'academia.edu', send_page_view: false, }); gtag('event', 'page_view', { 'controller': "profiles/works", 'action': "summary", 'controller_action': 'profiles/works#summary', 'logged_in': 'false', 'edge': 'unknown', // Send nil if there is no A/B test bucket, in case some records get logged // with missing data - that way we can distinguish between the two cases. // ab_test_bucket should be of the form <ab_test_name>:<bucket> 'ab_test_bucket': null, }) </script> <script type="text/javascript"> window.sendUserTiming = function(timingName) { if (!(window.performance && window.performance.measure)) return; var entries = window.performance.getEntriesByName(timingName, "measure"); if (entries.length !== 1) return; var timingValue = Math.round(entries[0].duration); gtag('event', 'timing_complete', { name: timingName, value: timingValue, event_category: 'User-centric', }); }; window.sendUserTiming("Time To First Byte"); </script> <meta name="csrf-param" content="authenticity_token" /> <meta name="csrf-token" content="X16nAdDhN7hBmxxJZbwG/J+HqIO7W6z4CA3FFtlLvl6ym38QMcKB/fT9PtgWc3AMGkHp6Rh40/S7g5vM4mHH7g==" /> <link rel="stylesheet" media="all" href="//a.academia-assets.com/assets/wow-77f7b87cb1583fc59aa8f94756ebfe913345937eb932042b4077563bebb5fb4b.css" /><link rel="stylesheet" media="all" href="//a.academia-assets.com/assets/social/home-9e8218e1301001388038e3fc3427ed00d079a4760ff7745d1ec1b2d59103170a.css" /><link rel="stylesheet" media="all" href="//a.academia-assets.com/assets/design_system/heading-b2b823dd904da60a48fd1bfa1defd840610c2ff414d3f39ed3af46277ab8df3b.css" /><link rel="stylesheet" media="all" href="//a.academia-assets.com/assets/design_system/button-3cea6e0ad4715ed965c49bfb15dedfc632787b32ff6d8c3a474182b231146ab7.css" /><link crossorigin="" href="https://fonts.gstatic.com/" rel="preconnect" /><link href="https://fonts.googleapis.com/css2?family=DM+Sans:ital,opsz,wght@0,9..40,100..1000;1,9..40,100..1000&family=Gupter:wght@400;500;700&family=IBM+Plex+Mono:wght@300;400&family=Material+Symbols+Outlined:opsz,wght,FILL,GRAD@20,400,0,0&display=swap" rel="stylesheet" /><link rel="stylesheet" media="all" href="//a.academia-assets.com/assets/design_system/common-10fa40af19d25203774df2d4a03b9b5771b45109c2304968038e88a81d1215c5.css" /> <meta name="author" content="changki lee" /> <meta name="description" content="Changki Lee, Kangwon National University: 25 Followers, 15 Following, 115 Research papers. Research interests: GPU Computing and Deep Learning." /> <meta name="google-site-verification" content="bKJMBZA7E43xhDOopFZkssMMkBRjvYERV-NaN4R6mrs" /> <script> var $controller_name = 'works'; var $action_name = "summary"; var $rails_env = 'production'; var $app_rev = '9387f500ddcbb8d05c67bef28a2fe0334f1aafb8'; var $domain = 'academia.edu'; var $app_host = "academia.edu"; var $asset_host = "academia-assets.com"; var $start_time = new Date().getTime(); var $recaptcha_key = "6LdxlRMTAAAAADnu_zyLhLg0YF9uACwz78shpjJB"; var $recaptcha_invisible_key = "6Lf3KHUUAAAAACggoMpmGJdQDtiyrjVlvGJ6BbAj"; var $disableClientRecordHit = false; </script> <script> window.Aedu = { hit_data: null }; window.Aedu.SiteStats = {"premium_universities_count":15268,"monthly_visitors":"113 million","monthly_visitor_count":113692424,"monthly_visitor_count_in_millions":113,"user_count":277717104,"paper_count":55203019,"paper_count_in_millions":55,"page_count":432000000,"page_count_in_millions":432,"pdf_count":16500000,"pdf_count_in_millions":16}; window.Aedu.serverRenderTime = new Date(1733024437000); window.Aedu.timeDifference = new Date().getTime() - 1733024437000; window.Aedu.isUsingCssV1 = false; window.Aedu.enableLocalization = true; window.Aedu.activateFullstory = false; window.Aedu.serviceAvailability = { status: {"attention_db":"on","bibliography_db":"on","contacts_db":"on","email_db":"on","indexability_db":"on","mentions_db":"on","news_db":"on","notifications_db":"on","offsite_mentions_db":"on","redshift":"on","redshift_exports_db":"on","related_works_db":"on","ring_db":"on","user_tests_db":"on"}, serviceEnabled: function(service) { return this.status[service] === "on"; }, readEnabled: function(service) { return this.serviceEnabled(service) || this.status[service] === "read_only"; }, }; window.Aedu.viewApmTrace = function() { // Check if x-apm-trace-id meta tag is set, and open the trace in APM // in a new window if it is. var apmTraceId = document.head.querySelector('meta[name="x-apm-trace-id"]'); if (apmTraceId) { var traceId = apmTraceId.content; // Use trace ID to construct URL, an example URL looks like: // https://app.datadoghq.com/apm/traces?query=trace_id%31298410148923562634 var apmUrl = 'https://app.datadoghq.com/apm/traces?query=trace_id%3A' + traceId; window.open(apmUrl, '_blank'); } }; </script>  <link href="https://fonts.googleapis.com/css?family=Roboto:100,100i,300,300i,400,400i,500,500i,700,700i,900,900i" rel="stylesheet"> <link href="//maxcdn.bootstrapcdn.com/font-awesome/4.3.0/css/font-awesome.min.css" rel="stylesheet"> <link rel="stylesheet" media="all" href="//a.academia-assets.com/assets/libraries-a9675dcb01ec4ef6aa807ba772c7a5a00c1820d3ff661c1038a20f80d06bb4e4.css" /> <link rel="stylesheet" media="all" href="//a.academia-assets.com/assets/academia-bdb9e8c097f01e611f2fc5e2f1a9dc599beede975e2ae5629983543a1726e947.css" /> <link rel="stylesheet" media="all" href="//a.academia-assets.com/assets/design_system_legacy-056a9113b9a0f5343d013b29ee1929d5a18be35fdcdceb616600b4db8bd20054.css" /> <script src="//a.academia-assets.com/assets/webpack_bundles/runtime-bundle-005434038af4252ca37c527588411a3d6a0eabb5f727fac83f8bbe7fd88d93bb.js"></script> <script src="//a.academia-assets.com/assets/webpack_bundles/webpack_libraries_and_infrequently_changed.wjs-bundle-3e572e3b706c3ed2ec5b2c1cb44a411fadc81f62a97963cb7bd9c327a0a9d5f2.js"></script> <script src="//a.academia-assets.com/assets/webpack_bundles/core_webpack.wjs-bundle-2e8d3f30eaaddd1debd6ce4630b3453b23a23c91ac7c823ddf8822879835b029.js"></script> <script src="//a.academia-assets.com/assets/webpack_bundles/sentry.wjs-bundle-5fe03fddca915c8ba0f7edbe64c194308e8ce5abaed7bffe1255ff37549c4808.js"></script> <script> jade = window.jade || {}; jade.helpers = window.$h; jade._ = window._; </script>  <script id="tag-manager-head-root">(function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start': new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0], j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src= 'https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f); })(window,document,'script','dataLayer_old','GTM-5G9JF7Z');</script>  <script> window.gptadslots = []; window.googletag = window.googletag || {}; window.googletag.cmd = window.googletag.cmd || []; </script> <script type="text/javascript"> // TODO(jacob): This should be defined, may be rare load order problem. // Checking if null is just a quick fix, will default to en if unset. // Better fix is to run this immedietely after I18n is set. if (window.I18n != null) { I18n.defaultLocale = "en"; I18n.locale = "en"; I18n.fallbacks = true; } </script> <link rel="canonical" href="https://kangwon.academia.edu/ChangkiLee" /> </head>   <body class='c-profiles/works a-summary logged_out'>  <div id="fb-root"></div><script>window.fbAsyncInit = function() { FB.init({ appId: "2369844204", version: "v8.0", status: true, cookie: true, xfbml: true }); // Additional initialization code. if (window.InitFacebook) { // facebook.ts already loaded, set it up. window.InitFacebook(); } else { // Set a flag for facebook.ts to find when it loads. window.academiaAuthReadyFacebook = true; } };</script><script>window.fbAsyncLoad = function() { // Protection against double calling of this function if (window.FB) { return; } (function(d, s, id){ var js, fjs = d.getElementsByTagName(s)[0]; if (d.getElementById(id)) {return;} js = d.createElement(s); js.id = id; js.src = "//connect.facebook.net/en_US/sdk.js"; fjs.parentNode.insertBefore(js, fjs); }(document, 'script', 'facebook-jssdk')); } if (!window.defer_facebook) { // Autoload if not deferred window.fbAsyncLoad(); } else { // Defer loading by 5 seconds setTimeout(function() { window.fbAsyncLoad(); }, 5000); }</script> <div id="google-root"></div><script>window.loadGoogle = function() { if (window.InitGoogle) { // google.ts already loaded, set it up. window.InitGoogle("331998490334-rsn3chp12mbkiqhl6e7lu2q0mlbu0f1b"); } else { // Set a flag for google.ts to use when it loads. window.GoogleClientID = "331998490334-rsn3chp12mbkiqhl6e7lu2q0mlbu0f1b"; } };</script><script>window.googleAsyncLoad = function() { // Protection against double calling of this function (function(d) { var js; var id = 'google-jssdk'; var ref = d.getElementsByTagName('script')[0]; if (d.getElementById(id)) { return; } js = d.createElement('script'); js.id = id; js.async = true; js.onload = loadGoogle; js.src = "https://accounts.google.com/gsi/client" ref.parentNode.insertBefore(js, ref); }(document)); } if (!window.defer_google) { // Autoload if not deferred window.googleAsyncLoad(); } else { // Defer loading by 5 seconds setTimeout(function() { window.googleAsyncLoad(); }, 5000); }</script> <div id="tag-manager-body-root">  <noscript><iframe src="https://www.googletagmanager.com/ns.html?id=GTM-5G9JF7Z" height="0" width="0" style="display:none;visibility:hidden"></iframe></noscript>   <script> window.addEventListener('load', function() { if (document.querySelector('input[name="commit"]')) { document.querySelector('input[name="commit"]').addEventListener('click', function() { gtag('event', 'click', { event_category: 'button', event_label: 'Log In' }) }) } }); </script> </div> <script>var _comscore = _comscore || []; _comscore.push({ c1: "2", c2: "26766707" }); (function() { var s = document.createElement("script"), el = document.getElementsByTagName("script")[0]; s.async = true; s.src = (document.location.protocol == "https:" ? "https://sb" : "http://b") + ".scorecardresearch.com/beacon.js"; el.parentNode.insertBefore(s, el); })();</script><img src="https://sb.scorecardresearch.com/p?c1=2&c2=26766707&cv=2.0&cj=1" style="position: absolute; visibility: hidden" /> <div id='react-modal'></div> <div class='DesignSystem'> <a class='u-showOnFocus' href='#site'> Skip to main content </a> </div> <div id="upgrade_ie_banner" style="display: none;"><p>Academia.edu no longer supports Internet Explorer.</p><p>To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to <a href="https://www.academia.edu/upgrade-browser">upgrade your browser</a>.</p></div><script>// Show this banner for all versions of IE if (!!window.MSInputMethodContext || /(MSIE)/.test(navigator.userAgent)) { document.getElementById('upgrade_ie_banner').style.display = 'block'; }</script> <div class="DesignSystem bootstrap ShrinkableNav"><div class="navbar navbar-default main-header"><div class="container-wrapper" id="main-header-container"><div class="container"><div class="navbar-header"><div class="nav-left-wrapper u-mt0x"><div class="nav-logo"><a data-main-header-link-target="logo_home" href="https://www.academia.edu/"><img class="visible-xs-inline-block" style="height: 24px;" alt="Academia.edu" src="//a.academia-assets.com/images/academia-logo-redesign-2015-A.svg" width="24" height="24" /><img width="145.2" height="18" class="hidden-xs" style="height: 24px;" alt="Academia.edu" src="//a.academia-assets.com/images/academia-logo-redesign-2015.svg" /></a></div><div class="nav-search"><div class="SiteSearch-wrapper select2-no-default-pills"><form class="js-SiteSearch-form DesignSystem" action="https://www.academia.edu/search" accept-charset="UTF-8" method="get"><input name="utf8" type="hidden" value="✓" autocomplete="off" /><i class="SiteSearch-icon fa fa-search u-fw700 u-positionAbsolute u-tcGrayDark"></i><input class="js-SiteSearch-form-input SiteSearch-form-input form-control" data-main-header-click-target="search_input" name="q" placeholder="Search" type="text" value="" /></form></div></div></div><div class="nav-right-wrapper pull-right"><ul class="NavLinks js-main-nav list-unstyled"><li class="NavLinks-link"><a class="js-header-login-url Button Button--inverseGray Button--sm u-mb4x" id="nav_log_in" rel="nofollow" href="https://www.academia.edu/login">Log In</a></li><li class="NavLinks-link u-p0x"><a class="Button Button--inverseGray Button--sm u-mb4x" rel="nofollow" href="https://www.academia.edu/signup">Sign Up</a></li></ul><button class="hidden-lg hidden-md hidden-sm u-ml4x navbar-toggle collapsed" data-target=".js-mobile-header-links" data-toggle="collapse" type="button"><span class="icon-bar"></span><span class="icon-bar"></span><span class="icon-bar"></span></button></div></div><div class="collapse navbar-collapse js-mobile-header-links"><ul class="nav navbar-nav"><li class="u-borderColorGrayLight u-borderBottom1"><a rel="nofollow" href="https://www.academia.edu/login">Log In</a></li><li class="u-borderColorGrayLight u-borderBottom1"><a rel="nofollow" href="https://www.academia.edu/signup">Sign Up</a></li><li class="u-borderColorGrayLight u-borderBottom1 js-mobile-nav-expand-trigger"><a href="#">more&nbsp<span class="caret"></span></a></li><li><ul class="js-mobile-nav-expand-section nav navbar-nav u-m0x collapse"><li class="u-borderColorGrayLight u-borderBottom1"><a rel="false" href="https://www.academia.edu/about">About</a></li><li class="u-borderColorGrayLight u-borderBottom1"><a rel="nofollow" href="https://www.academia.edu/press">Press</a></li><li class="u-borderColorGrayLight u-borderBottom1"><a rel="nofollow" href="https://medium.com/@academia">Blog</a></li><li class="u-borderColorGrayLight u-borderBottom1"><a rel="false" href="https://www.academia.edu/documents">Papers</a></li><li class="u-borderColorGrayLight u-borderBottom1"><a rel="nofollow" href="https://www.academia.edu/terms">Terms</a></li><li class="u-borderColorGrayLight u-borderBottom1"><a rel="nofollow" href="https://www.academia.edu/privacy">Privacy</a></li><li class="u-borderColorGrayLight u-borderBottom1"><a rel="nofollow" href="https://www.academia.edu/copyright">Copyright</a></li><li class="u-borderColorGrayLight u-borderBottom1"><a rel="nofollow" href="https://www.academia.edu/hiring"><i class="fa fa-briefcase"></i> We're Hiring!</a></li><li class="u-borderColorGrayLight u-borderBottom1"><a rel="nofollow" href="https://support.academia.edu/"><i class="fa fa-question-circle"></i> Help Center</a></li><li class="js-mobile-nav-collapse-trigger u-borderColorGrayLight u-borderBottom1 dropup" style="display:none"><a href="#">less&nbsp<span class="caret"></span></a></li></ul></li></ul></div></div></div><script>(function(){ var $moreLink = $(".js-mobile-nav-expand-trigger"); var $lessLink = $(".js-mobile-nav-collapse-trigger"); var $section = $('.js-mobile-nav-expand-section'); $moreLink.click(function(ev){ ev.preventDefault(); $moreLink.hide(); $lessLink.show(); $section.collapse('show'); }); $lessLink.click(function(ev){ ev.preventDefault(); $moreLink.show(); $lessLink.hide(); $section.collapse('hide'); }); })() if ($a.is_logged_in() || false) { new Aedu.NavigationController({ el: '.js-main-nav', showHighlightedNotification: false }); } else { $(".js-header-login-url").attr("href", $a.loginUrlWithRedirect()); } Aedu.autocompleteSearch = new AutocompleteSearch({el: '.js-SiteSearch-form'});</script></div></div> <div id='site' class='fixed'> <div id="content" class="clearfix"> <script>document.addEventListener('DOMContentLoaded', function(){ var $dismissible = $(".dismissible_banner"); $dismissible.click(function(ev) { $dismissible.hide(); }); });</script> <script src="//a.academia-assets.com/assets/webpack_bundles/profile.wjs-bundle-ae3d0ee232cd83d11499343688b0160a3c7db15e95cb2d0844cae78d49ea53f1.js" defer="defer"></script><script>Aedu.rankings = { showPaperRankingsLink: false } $viewedUser = Aedu.User.set_viewed( {"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee","photo":"/images/s65_no_pic.png","has_photo":false,"department":{"id":1627388,"name":"CS","url":"https://kangwon.academia.edu/Departments/CS/Documents","university":{"id":8628,"name":"Kangwon National University","url":"https://kangwon.academia.edu/"}},"position":"Faculty Member","position_id":1,"is_analytics_public":false,"interests":[{"id":12225,"name":"GPU Computing","url":"https://www.academia.edu/Documents/in/GPU_Computing"},{"id":81182,"name":"Deep Learning","url":"https://www.academia.edu/Documents/in/Deep_Learning"}]} ); if ($a.is_logged_in() && $viewedUser.is_current_user()) { $('body').addClass('profile-viewed-by-owner'); } $socialProfiles = [{"id":14497569,"link":"https://www.facebook.com/app_scoped_user_id/896499967069903/","name":"Facebook","link_domain":"www.facebook.com","icon":"//www.google.com/s2/u/0/favicons?domain=www.facebook.com"}]</script><div id="js-react-on-rails-context" style="display:none" data-rails-context="{"inMailer":false,"i18nLocale":"en","i18nDefaultLocale":"en","href":"https://kangwon.academia.edu/ChangkiLee","location":"/ChangkiLee","scheme":"https","host":"kangwon.academia.edu","port":null,"pathname":"/ChangkiLee","search":null,"httpAcceptLanguage":null,"serverSide":false}"></div> <div class="js-react-on-rails-component" style="display:none" data-component-name="ProfileCheckPaperUpdate" data-props="{}" data-trace="false" data-dom-id="ProfileCheckPaperUpdate-react-component-f5634836-dd40-4dcc-86db-bb9b7373d209"></div> <div id="ProfileCheckPaperUpdate-react-component-f5634836-dd40-4dcc-86db-bb9b7373d209"></div> <div class="DesignSystem"><div class="onsite-ping" id="onsite-ping"></div></div><div class="profile-user-info DesignSystem"><div class="social-profile-container"><div class="left-panel-container"><div class="user-info-component-wrapper"><div class="user-summary-cta-container"><div class="user-summary-container"><div class="social-profile-avatar-container"><img class="profile-avatar u-positionAbsolute" border="0" alt="" src="//a.academia-assets.com/images/s200_no_pic.png" /></div><div class="title-container"><h1 class="ds2-5-heading-sans-serif-sm">Changki Lee</h1><div class="affiliations-container fake-truncate js-profile-affiliations"><div><a class="u-tcGrayDarker" href="https://kangwon.academia.edu/">Kangwon National University</a>, <a class="u-tcGrayDarker" href="https://kangwon.academia.edu/Departments/CS/Documents">CS</a>, <span class="u-tcGrayDarker">Faculty Member</span></div></div></div></div><div class="sidebar-cta-container"><button class="ds2-5-button hidden profile-cta-button grow js-profile-follow-button" data-broccoli-component="user-info.follow-button" data-click-track="profile-user-info-follow-button" data-follow-user-fname="Changki" data-follow-user-id="34012167" data-follow-user-source="profile_button" data-has-google="false"><span class="material-symbols-outlined" style="font-size: 20px" translate="no">add</span>Follow</button><button class="ds2-5-button hidden profile-cta-button grow js-profile-unfollow-button" data-broccoli-component="user-info.unfollow-button" data-click-track="profile-user-info-unfollow-button" data-unfollow-user-id="34012167"><span class="material-symbols-outlined" style="font-size: 20px" translate="no">done</span>Following</button></div></div><div class="user-stats-container"><a><div class="stat-container js-profile-followers"><p class="label">Followers</p><p class="data">25</p></div></a><a><div class="stat-container js-profile-followees" data-broccoli-component="user-info.followees-count" data-click-track="profile-expand-user-info-following"><p class="label">Following</p><p class="data">15</p></div></a><a href="/ChangkiLee/mentions"><div class="stat-container"><p class="label">Mentions</p><p class="data">1</p></div></a><span><div class="stat-container"><p class="label"><span class="js-profile-total-view-text">Public Views</span></p><p class="data"><span class="js-profile-view-count"></span></p></div></span></div><div class="ri-section"><div class="ri-section-header"><span>Interests</span></div><div class="ri-tags-container"><a data-click-track="profile-user-info-expand-research-interests" data-has-card-for-ri-list="34012167" href="https://www.academia.edu/Documents/in/GPU_Computing"><div id="js-react-on-rails-context" style="display:none" data-rails-context="{"inMailer":false,"i18nLocale":"en","i18nDefaultLocale":"en","href":"https://kangwon.academia.edu/ChangkiLee","location":"/ChangkiLee","scheme":"https","host":"kangwon.academia.edu","port":null,"pathname":"/ChangkiLee","search":null,"httpAcceptLanguage":null,"serverSide":false}"></div> <div class="js-react-on-rails-component" style="display:none" data-component-name="Pill" data-props="{"color":"gray","children":["GPU Computing"]}" data-trace="false" data-dom-id="Pill-react-component-09d32a23-1286-4191-9093-6a832cdc967c"></div> <div id="Pill-react-component-09d32a23-1286-4191-9093-6a832cdc967c"></div> </a><a data-click-track="profile-user-info-expand-research-interests" data-has-card-for-ri-list="34012167" href="https://www.academia.edu/Documents/in/Deep_Learning"><div class="js-react-on-rails-component" style="display:none" data-component-name="Pill" data-props="{"color":"gray","children":["Deep Learning"]}" data-trace="false" data-dom-id="Pill-react-component-00a9ccb9-e66a-4f8c-9189-205f3b910d66"></div> <div id="Pill-react-component-00a9ccb9-e66a-4f8c-9189-205f3b910d66"></div> </a></div></div><div class="external-links-container"><ul class="profile-links new-profile js-UserInfo-social"><li class="profile-profiles js-social-profiles-container"><i class="fa fa-spin fa-spinner"></i></li></ul></div></div></div><div class="right-panel-container"><div class="user-content-wrapper"><div class="uploads-container" id="social-redesign-work-container"><div class="upload-header"><h2 class="ds2-5-heading-sans-serif-xs">Uploads</h2></div><div class="documents-container backbone-social-profile-documents" style="width: 100%;"><div class="u-taCenter"></div><div class="profile--tab_content_container js-tab-pane tab-pane active" id="all"><div class="profile--tab_heading_container js-section-heading" data-section="Papers" id="Papers"><h3 class="profile--tab_heading_container">Papers by Changki Lee</h3></div><div class="js-work-strip profile--work_container" data-work-id="96477146"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/96477146/Transformer_Decoding_Speed_Improvement_using_CAN_and_Dense_Synthesizer"><img alt="Research paper thumbnail of Transformer Decoding Speed Improvement using CAN and Dense Synthesizer" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/96477146/Transformer_Decoding_Speed_Improvement_using_CAN_and_Dense_Synthesizer">Transformer Decoding Speed Improvement using CAN and Dense Synthesizer</a></div><div class="wp-workCard_item"><span>KIISE Transactions on Computing Practices</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="96477146"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="96477146"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 96477146; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=96477146]").text(description); $(".js-view-count[data-work-id=96477146]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 96477146; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='96477146']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 96477146, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=96477146]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":96477146,"title":"Transformer Decoding Speed Improvement using CAN and Dense Synthesizer","translated_title":"","metadata":{"publisher":"Korean Institute of Information Scientists and Engineers","publication_name":"KIISE Transactions on Computing Practices"},"translated_abstract":null,"internal_url":"https://www.academia.edu/96477146/Transformer_Decoding_Speed_Improvement_using_CAN_and_Dense_Synthesizer","translated_internal_url":"","created_at":"2023-02-07T07:13:52.530-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Transformer_Decoding_Speed_Improvement_using_CAN_and_Dense_Synthesizer","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":117893,"name":"Transformer","url":"https://www.academia.edu/Documents/in/Transformer"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="96477145"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/96477145/Coreference_Resolution_with_Hierarchical_Pointer_Networks_Based_on_Pointing_Methods"><img alt="Research paper thumbnail of Coreference Resolution with Hierarchical Pointer Networks Based on Pointing Methods" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/96477145/Coreference_Resolution_with_Hierarchical_Pointer_Networks_Based_on_Pointing_Methods">Coreference Resolution with Hierarchical Pointer Networks Based on Pointing Methods</a></div><div class="wp-workCard_item"><span>2020 IEEE International Conference on Big Data and Smart Computing (BigComp)</span><span>, 2020</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Coreference resolution is a type of discourse analysis task of natural language processing. The t...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">Coreference resolution is a type of discourse analysis task of natural language processing. The task entails a method of linking different words expressed in an arbitrary entity within a document. Pointer networks (Ptr-net) based on RNN encoder-decoder is capable of modeling the problem of a target class variable and learning and predicting a position corresponding to a given input sequence. A hierarchical RNN encoder-decoder is an extended model of the RNN encoder-decoder that performs encoding on a word-by-word basis for a given input sequence. It performs encoding on a sentence basis to predict the output result. Ptr-net suffers from performance degradation when the input is composed of multiple sentences, or when the length of the input sentence is long. To solve this problem, we propose a coreference resolution with a hierarchical pointer networks (HRPT) model based on pointing methods for all cases mentioned. The HRPT encodes word and sentence levels for the input sequence, consisting of multiple sentences. It uses both word and sentence-level information in the decoder. The pointing method for coreference resolution is a way of pointing to the position of the referenced word or the referenced pivot of the entity. Experimental results show that the proposed model is CoNLL F1 71.56%, which is 20.96% better than the rule-based model.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="96477145"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="96477145"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 96477145; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=96477145]").text(description); $(".js-view-count[data-work-id=96477145]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 96477145; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='96477145']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 96477145, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=96477145]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":96477145,"title":"Coreference Resolution with Hierarchical Pointer Networks Based on Pointing Methods","translated_title":"","metadata":{"abstract":"Coreference resolution is a type of discourse analysis task of natural language processing. The task entails a method of linking different words expressed in an arbitrary entity within a document. Pointer networks (Ptr-net) based on RNN encoder-decoder is capable of modeling the problem of a target class variable and learning and predicting a position corresponding to a given input sequence. A hierarchical RNN encoder-decoder is an extended model of the RNN encoder-decoder that performs encoding on a word-by-word basis for a given input sequence. It performs encoding on a sentence basis to predict the output result. Ptr-net suffers from performance degradation when the input is composed of multiple sentences, or when the length of the input sentence is long. To solve this problem, we propose a coreference resolution with a hierarchical pointer networks (HRPT) model based on pointing methods for all cases mentioned. The HRPT encodes word and sentence levels for the input sequence, consisting of multiple sentences. It uses both word and sentence-level information in the decoder. The pointing method for coreference resolution is a way of pointing to the position of the referenced word or the referenced pivot of the entity. Experimental results show that the proposed model is CoNLL F1 71.56%, which is 20.96% better than the rule-based model.","publisher":"IEEE","publication_date":{"day":null,"month":null,"year":2020,"errors":{}},"publication_name":"2020 IEEE International Conference on Big Data and Smart Computing (BigComp)"},"translated_abstract":"Coreference resolution is a type of discourse analysis task of natural language processing. The task entails a method of linking different words expressed in an arbitrary entity within a document. Pointer networks (Ptr-net) based on RNN encoder-decoder is capable of modeling the problem of a target class variable and learning and predicting a position corresponding to a given input sequence. A hierarchical RNN encoder-decoder is an extended model of the RNN encoder-decoder that performs encoding on a word-by-word basis for a given input sequence. It performs encoding on a sentence basis to predict the output result. Ptr-net suffers from performance degradation when the input is composed of multiple sentences, or when the length of the input sentence is long. To solve this problem, we propose a coreference resolution with a hierarchical pointer networks (HRPT) model based on pointing methods for all cases mentioned. The HRPT encodes word and sentence levels for the input sequence, consisting of multiple sentences. It uses both word and sentence-level information in the decoder. The pointing method for coreference resolution is a way of pointing to the position of the referenced word or the referenced pivot of the entity. Experimental results show that the proposed model is CoNLL F1 71.56%, which is 20.96% better than the rule-based model.","internal_url":"https://www.academia.edu/96477145/Coreference_Resolution_with_Hierarchical_Pointer_Networks_Based_on_Pointing_Methods","translated_internal_url":"","created_at":"2023-02-07T07:13:52.352-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Coreference_Resolution_with_Hierarchical_Pointer_Networks_Based_on_Pointing_Methods","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":60944,"name":"Coreference","url":"https://www.academia.edu/Documents/in/Coreference"},{"id":140897,"name":"Encoder","url":"https://www.academia.edu/Documents/in/Encoder"},{"id":961850,"name":"Sentence","url":"https://www.academia.edu/Documents/in/Sentence"}],"urls":[{"id":28771720,"url":"http://xplorestaging.ieee.org/ielx7/9050588/9070238/09070417.pdf?arnumber=9070417"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="96477144"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/96477144/S_2_Net_Machine_reading_comprehension_with_SRU_based_self_matching_networks"><img alt="Research paper thumbnail of S 2 ‐Net: Machine reading comprehension with SRU‐based self‐matching networks" class="work-thumbnail" src="https://attachments.academia-assets.com/98365356/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/96477144/S_2_Net_Machine_reading_comprehension_with_SRU_based_self_matching_networks">S 2 ‐Net: Machine reading comprehension with SRU‐based self‐matching networks</a></div><div class="wp-workCard_item"><span>ETRI Journal</span><span>, 2019</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="b114eeeb083aae23c8154e055df26e1a" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":98365356,"asset_id":96477144,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/98365356/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="96477144"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="96477144"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 96477144; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=96477144]").text(description); $(".js-view-count[data-work-id=96477144]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 96477144; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='96477144']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 96477144, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "b114eeeb083aae23c8154e055df26e1a" } } $('.js-work-strip[data-work-id=96477144]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":96477144,"title":"S 2 ‐Net: Machine reading comprehension with SRU‐based self‐matching networks","translated_title":"","metadata":{"publisher":"Wiley","grobid_abstract":"Machine reading comprehension refers to a machine's ability to understand a given context and determine the correct answer to a question in the context of question-answering applications. For example, machine reading comprehension should be able to understand the context \"2004년 건조기 시 장에… 의류 건조기 중 LG전자는 점유율 77.4%로 1위를 차지했다. (Machine dryer market in 2004 … LG Electronics ranked first with 77.4% of clothes dryers.)\" and determine the correct answer output \"LG 전자 (LG Electronics)\" in the context of a question like \"국내 건조기 시장 점유율 1 위 누구야? (Who is number 1 in the Korean dryer market share?)\". Machine reading comprehension has been performed on datasets, such as SQuAD of Stanford, bAbi of Facebook, and MS-MARCO of Microsoft [1-3]. Deep-learning models, such as DrQA, fastQA, R-Net, AoA reader, bidirectional flow (BiDAF), and Match-LSTM [4-9], are currently the focus of research. These deep-learning models perform encoding","publication_date":{"day":null,"month":null,"year":2019,"errors":{}},"publication_name":"ETRI Journal","grobid_abstract_attachment_id":98365356},"translated_abstract":null,"internal_url":"https://www.academia.edu/96477144/S_2_Net_Machine_reading_comprehension_with_SRU_based_self_matching_networks","translated_internal_url":"","created_at":"2023-02-07T07:13:52.132-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":98365356,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/98365356/thumbnails/1.jpg","file_name":"etrij.2017-027920230207-1-1vmw5pm.pdf","download_url":"https://www.academia.edu/attachments/98365356/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"S_2_Net_Machine_reading_comprehension_wi.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/98365356/etrij.2017-027920230207-1-1vmw5pm-libre.pdf?1675786271=\u0026response-content-disposition=attachment%3B+filename%3DS_2_Net_Machine_reading_comprehension_wi.pdf\u0026Expires=1733028036\u0026Signature=XyMY1Na3ppokYVyK4sLa04lSgLXZN8nKpkSK5X9c2A29YbrYPH67~HPKOojtq0I5PfcvA8OjfQCUf~Fr6WKbBkZqPl83inkUdBNrDB94KlE9mb4wmpZTES32qPLylog7gfD4byD0otj6THaQF59VSj75GPS2cUnn4Y~u3awF4TrFFUHDmkuY3fdD7HPG0e9y0TgmG1v6udOJpZ4wWQ5dVpa2ZeEWH44zDLSl0lp1belVGboNRh9z~oMJP00pxpQI8kuDs3Cup4-Cugvcc9uxIgj74j4JKWUhj27q7EsOfYsYxQYJBOcJxj1IhBic3pTfUXWLeHkoF3VA5WzxdXB0oQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"S_2_Net_Machine_reading_comprehension_with_SRU_based_self_matching_networks","translated_slug":"","page_count":12,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":98365356,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/98365356/thumbnails/1.jpg","file_name":"etrij.2017-027920230207-1-1vmw5pm.pdf","download_url":"https://www.academia.edu/attachments/98365356/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"S_2_Net_Machine_reading_comprehension_wi.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/98365356/etrij.2017-027920230207-1-1vmw5pm-libre.pdf?1675786271=\u0026response-content-disposition=attachment%3B+filename%3DS_2_Net_Machine_reading_comprehension_wi.pdf\u0026Expires=1733028036\u0026Signature=XyMY1Na3ppokYVyK4sLa04lSgLXZN8nKpkSK5X9c2A29YbrYPH67~HPKOojtq0I5PfcvA8OjfQCUf~Fr6WKbBkZqPl83inkUdBNrDB94KlE9mb4wmpZTES32qPLylog7gfD4byD0otj6THaQF59VSj75GPS2cUnn4Y~u3awF4TrFFUHDmkuY3fdD7HPG0e9y0TgmG1v6udOJpZ4wWQ5dVpa2ZeEWH44zDLSl0lp1belVGboNRh9z~oMJP00pxpQI8kuDs3Cup4-Cugvcc9uxIgj74j4JKWUhj27q7EsOfYsYxQYJBOcJxj1IhBic3pTfUXWLeHkoF3VA5WzxdXB0oQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":37,"name":"Information Systems","url":"https://www.academia.edu/Documents/in/Information_Systems"},{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":1237788,"name":"Electrical And Electronic Engineering","url":"https://www.academia.edu/Documents/in/Electrical_And_Electronic_Engineering"}],"urls":[{"id":28771719,"url":"https://onlinelibrary.wiley.com/doi/pdf/10.4218/etrij.2017-0279"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="96477143"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/96477143/Dependency_structure_language_model_for_topic_detection_and_tracking"><img alt="Research paper thumbnail of Dependency structure language model for topic detection and tracking" class="work-thumbnail" src="https://attachments.academia-assets.com/98365401/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/96477143/Dependency_structure_language_model_for_topic_detection_and_tracking">Dependency structure language model for topic detection and tracking</a></div><div class="wp-workCard_item"><span>Information Processing &amp; Management</span><span>, 2007</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="4f976a76bafc5842d3c13272d7424da6" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":98365401,"asset_id":96477143,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/98365401/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="96477143"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="96477143"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 96477143; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=96477143]").text(description); $(".js-view-count[data-work-id=96477143]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 96477143; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='96477143']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 96477143, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "4f976a76bafc5842d3c13272d7424da6" } } $('.js-work-strip[data-work-id=96477143]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":96477143,"title":"Dependency structure language model for topic detection and tracking","translated_title":"","metadata":{"publisher":"Elsevier BV","grobid_abstract":"In this paper, we propose a new language model, namely, a dependency structure language model, for topic detection and tracking (TDT) to compensate for weakness of unigram and bigram language models. The dependency structure language model is based on the Chow expansion theory and the dependency parse tree generated by a linguistic parser. So, long-distance dependencies can be naturally captured by the dependency structure language model. We carried out extensive experiments to verify the proposed model on topic tracking and link detection in TDT. In both cases, the dependency structure language models perform better than strong baseline approaches.","publication_date":{"day":null,"month":null,"year":2007,"errors":{}},"publication_name":"Information Processing \u0026amp; Management","grobid_abstract_attachment_id":98365401},"translated_abstract":null,"internal_url":"https://www.academia.edu/96477143/Dependency_structure_language_model_for_topic_detection_and_tracking","translated_internal_url":"","created_at":"2023-02-07T07:13:51.952-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":98365401,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/98365401/thumbnails/1.jpg","file_name":"j.ipm.2006.02.00720230207-1-3er8pv.pdf","download_url":"https://www.academia.edu/attachments/98365401/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Dependency_structure_language_model_for.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/98365401/j.ipm.2006.02.00720230207-1-3er8pv-libre.pdf?1675786271=\u0026response-content-disposition=attachment%3B+filename%3DDependency_structure_language_model_for.pdf\u0026Expires=1733028036\u0026Signature=bCkLzzpjZl4fio0IqPan4R37nKQnA4ovStLzkg7o1mVoJYRqmef~PI3u0RYsbxS8gbLwRzb8EOaxY0VInKFUOA1ROF5rJj9KAAzOa9xjIqs7gEBA47iMpbh9HYAN~r151GuM5ic3eBZStmk7eLb95bSRiNzYh94KdxYa3vkYPMElo83ed4oTq3ijgcUOr2aN3-52mswsAgwQgH5q7roVPBwHbzH1tTjUyajCKZPth4PePGiOxrBioMIe~xendekmUTnceJwSBugExxW-zSBuyz0nzA0p-aMEfgCY-Bj0IdANo39rAVZkMGOcn1FFxox6R5X7QoxbcxyjPrDBTm7ZqQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Dependency_structure_language_model_for_topic_detection_and_tracking","translated_slug":"","page_count":11,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":98365401,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/98365401/thumbnails/1.jpg","file_name":"j.ipm.2006.02.00720230207-1-3er8pv.pdf","download_url":"https://www.academia.edu/attachments/98365401/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Dependency_structure_language_model_for.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/98365401/j.ipm.2006.02.00720230207-1-3er8pv-libre.pdf?1675786271=\u0026response-content-disposition=attachment%3B+filename%3DDependency_structure_language_model_for.pdf\u0026Expires=1733028036\u0026Signature=bCkLzzpjZl4fio0IqPan4R37nKQnA4ovStLzkg7o1mVoJYRqmef~PI3u0RYsbxS8gbLwRzb8EOaxY0VInKFUOA1ROF5rJj9KAAzOa9xjIqs7gEBA47iMpbh9HYAN~r151GuM5ic3eBZStmk7eLb95bSRiNzYh94KdxYa3vkYPMElo83ed4oTq3ijgcUOr2aN3-52mswsAgwQgH5q7roVPBwHbzH1tTjUyajCKZPth4PePGiOxrBioMIe~xendekmUTnceJwSBugExxW-zSBuyz0nzA0p-aMEfgCY-Bj0IdANo39rAVZkMGOcn1FFxox6R5X7QoxbcxyjPrDBTm7ZqQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":37,"name":"Information Systems","url":"https://www.academia.edu/Documents/in/Information_Systems"},{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":464,"name":"Information Retrieval","url":"https://www.academia.edu/Documents/in/Information_Retrieval"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":3268,"name":"Computational Linguistics","url":"https://www.academia.edu/Documents/in/Computational_Linguistics"},{"id":11128,"name":"Information Extraction","url":"https://www.academia.edu/Documents/in/Information_Extraction"},{"id":14493,"name":"Parsing","url":"https://www.academia.edu/Documents/in/Parsing"},{"id":59587,"name":"Library and Information Studies","url":"https://www.academia.edu/Documents/in/Library_and_Information_Studies"},{"id":238516,"name":"Topic Detection and Tracking","url":"https://www.academia.edu/Documents/in/Topic_Detection_and_Tracking"},{"id":297057,"name":"Dependency Parsing","url":"https://www.academia.edu/Documents/in/Dependency_Parsing"},{"id":520672,"name":"Language Model","url":"https://www.academia.edu/Documents/in/Language_Model"},{"id":2467595,"name":"Probabilistic Model","url":"https://www.academia.edu/Documents/in/Probabilistic_Model"},{"id":3516262,"name":"Dependency Grammar","url":"https://www.academia.edu/Documents/in/Dependency_Grammar"},{"id":3806420,"name":"bigram","url":"https://www.academia.edu/Documents/in/bigram"}],"urls":[{"id":28771718,"url":"https://api.elsevier.com/content/article/PII:S0306457306000203?httpAccept=text/xml"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="96477044"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/96477044/Extending_Korean_PropBank_for_Korean_Semantic_Role_Labeling_and_Applying_Domain_Adaptation_Technique"><img alt="Research paper thumbnail of Extending Korean PropBank for Korean Semantic Role Labeling and Applying Domain Adaptation Technique" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/96477044/Extending_Korean_PropBank_for_Korean_Semantic_Role_Labeling_and_Applying_Domain_Adaptation_Technique">Extending Korean PropBank for Korean Semantic Role Labeling and Applying Domain Adaptation Technique</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">1. 서론 의미역 결정(Semantic Role Labeling)은 문장의 각 술 어의 의미와 그 논항들의 의미적인 관계를 결정하는 자 연 언어 처리의 한 단계이다. 의미역 ...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">1. 서론 의미역 결정(Semantic Role Labeling)은 문장의 각 술 어의 의미와 그 논항들의 의미적인 관계를 결정하는 자 연 언어 처리의 한 단계이다. 의미역 결정은 일반적으로 기계 학습에 의해 이루어지게 되며 현재까지 연구가 활 발하게 진행되고 있다. 일반적인 기계 학습 기반의 의미역 결정 시스템은 해당 문장의 술어들을 식별하고 각 술어에 대한 논항들의 의 미역을 결정하여 “누가, 무엇을, 누구에게, 어떻게, 왜”등의 의미 관계를 찾아내는 시스템이다. 예를 들면 그림 1 의 ‘상어는 연골어류에 속하는 물고기이다.’와 같은 텍스트로 된 문장이 주어졌을 때 의미역 결정 시스 템에 의해 ‘속하.01’이라는 술어와 의미역이 달린 술 어의 논항들을 얻게 된다. 여기서 ‘NR’은 의미역이 달 리지 않았음을 뜻하고 ‘ARG1’은 술어 ‘속하.01’의 논항이 된다. 의미역 결정 시스템은 기계 학습에 필요한 많은 양의 말뭉치를 필요로 한다. 의미역 결정 시스템에서 널리 사 용되는 말뭉치로 PropBank[1]가 있으나 이는 영어 의미 역 결정을 위한 말뭉치이기 때문에 한국어에 적용할 수 없다. 이를 해결하기 위해 Korean PropBank[2]가 만들어 졌으나 의미역 부착 말뭉치와 동사 격틀이 영어 PropBank의 1/8 수준에 불과하다. 따라서 본 논문에서는 한국어 Wikipedia에서 추출한 데이터를 이용하여 Korean PropBank를 확장하고자 한다. 의미역 결정 시스템은 크 게 격틀 사전에 기반을 둔 시스템과 말뭉치에 기반을 둔 시스템으로 나눌 수 있으므로[3] Korean PropBank를 확 장하기 위해 본 논문에서는 말뭉치를 늘리는 방법과 격 틀 사전을 확장하는 방법 모두를 고려한다. 일반적인 의미역 결정 시스템은 학습에 사용한 데이터 와 테스트 데이터가 같은 도메인으로 이루어져 있다. 반 면 학습에 사용한 도메인과는 다른 도메인으로 테스트를 할 경우 의미역 결정 시스템 성능이 큰 폭으로 하락됨을 볼 수 있다.[4] 의미역 결정 시스템...</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="96477044"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="96477044"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 96477044; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=96477044]").text(description); $(".js-view-count[data-work-id=96477044]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 96477044; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='96477044']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 96477044, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=96477044]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":96477044,"title":"Extending Korean PropBank for Korean Semantic Role Labeling and Applying Domain Adaptation Technique","translated_title":"","metadata":{"abstract":"1. 서론 의미역 결정(Semantic Role Labeling)은 문장의 각 술 어의 의미와 그 논항들의 의미적인 관계를 결정하는 자 연 언어 처리의 한 단계이다. 의미역 결정은 일반적으로 기계 학습에 의해 이루어지게 되며 현재까지 연구가 활 발하게 진행되고 있다. 일반적인 기계 학습 기반의 의미역 결정 시스템은 해당 문장의 술어들을 식별하고 각 술어에 대한 논항들의 의 미역을 결정하여 “누가, 무엇을, 누구에게, 어떻게, 왜”등의 의미 관계를 찾아내는 시스템이다. 예를 들면 그림 1 의 ‘상어는 연골어류에 속하는 물고기이다.’와 같은 텍스트로 된 문장이 주어졌을 때 의미역 결정 시스 템에 의해 ‘속하.01’이라는 술어와 의미역이 달린 술 어의 논항들을 얻게 된다. 여기서 ‘NR’은 의미역이 달 리지 않았음을 뜻하고 ‘ARG1’은 술어 ‘속하.01’의 논항이 된다. 의미역 결정 시스템은 기계 학습에 필요한 많은 양의 말뭉치를 필요로 한다. 의미역 결정 시스템에서 널리 사 용되는 말뭉치로 PropBank[1]가 있으나 이는 영어 의미 역 결정을 위한 말뭉치이기 때문에 한국어에 적용할 수 없다. 이를 해결하기 위해 Korean PropBank[2]가 만들어 졌으나 의미역 부착 말뭉치와 동사 격틀이 영어 PropBank의 1/8 수준에 불과하다. 따라서 본 논문에서는 한국어 Wikipedia에서 추출한 데이터를 이용하여 Korean PropBank를 확장하고자 한다. 의미역 결정 시스템은 크 게 격틀 사전에 기반을 둔 시스템과 말뭉치에 기반을 둔 시스템으로 나눌 수 있으므로[3] Korean PropBank를 확 장하기 위해 본 논문에서는 말뭉치를 늘리는 방법과 격 틀 사전을 확장하는 방법 모두를 고려한다. 일반적인 의미역 결정 시스템은 학습에 사용한 데이터 와 테스트 데이터가 같은 도메인으로 이루어져 있다. 반 면 학습에 사용한 도메인과는 다른 도메인으로 테스트를 할 경우 의미역 결정 시스템 성능이 큰 폭으로 하락됨을 볼 수 있다.[4] 의미역 결정 시스템...","publication_date":{"day":null,"month":null,"year":2014,"errors":{}}},"translated_abstract":"1. 서론 의미역 결정(Semantic Role Labeling)은 문장의 각 술 어의 의미와 그 논항들의 의미적인 관계를 결정하는 자 연 언어 처리의 한 단계이다. 의미역 결정은 일반적으로 기계 학습에 의해 이루어지게 되며 현재까지 연구가 활 발하게 진행되고 있다. 일반적인 기계 학습 기반의 의미역 결정 시스템은 해당 문장의 술어들을 식별하고 각 술어에 대한 논항들의 의 미역을 결정하여 “누가, 무엇을, 누구에게, 어떻게, 왜”등의 의미 관계를 찾아내는 시스템이다. 예를 들면 그림 1 의 ‘상어는 연골어류에 속하는 물고기이다.’와 같은 텍스트로 된 문장이 주어졌을 때 의미역 결정 시스 템에 의해 ‘속하.01’이라는 술어와 의미역이 달린 술 어의 논항들을 얻게 된다. 여기서 ‘NR’은 의미역이 달 리지 않았음을 뜻하고 ‘ARG1’은 술어 ‘속하.01’의 논항이 된다. 의미역 결정 시스템은 기계 학습에 필요한 많은 양의 말뭉치를 필요로 한다. 의미역 결정 시스템에서 널리 사 용되는 말뭉치로 PropBank[1]가 있으나 이는 영어 의미 역 결정을 위한 말뭉치이기 때문에 한국어에 적용할 수 없다. 이를 해결하기 위해 Korean PropBank[2]가 만들어 졌으나 의미역 부착 말뭉치와 동사 격틀이 영어 PropBank의 1/8 수준에 불과하다. 따라서 본 논문에서는 한국어 Wikipedia에서 추출한 데이터를 이용하여 Korean PropBank를 확장하고자 한다. 의미역 결정 시스템은 크 게 격틀 사전에 기반을 둔 시스템과 말뭉치에 기반을 둔 시스템으로 나눌 수 있으므로[3] Korean PropBank를 확 장하기 위해 본 논문에서는 말뭉치를 늘리는 방법과 격 틀 사전을 확장하는 방법 모두를 고려한다. 일반적인 의미역 결정 시스템은 학습에 사용한 데이터 와 테스트 데이터가 같은 도메인으로 이루어져 있다. 반 면 학습에 사용한 도메인과는 다른 도메인으로 테스트를 할 경우 의미역 결정 시스템 성능이 큰 폭으로 하락됨을 볼 수 있다.[4] 의미역 결정 시스템...","internal_url":"https://www.academia.edu/96477044/Extending_Korean_PropBank_for_Korean_Semantic_Role_Labeling_and_Applying_Domain_Adaptation_Technique","translated_internal_url":"","created_at":"2023-02-07T07:12:42.682-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Extending_Korean_PropBank_for_Korean_Semantic_Role_Labeling_and_Applying_Domain_Adaptation_Technique","translated_slug":"","page_count":null,"language":"ko","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":203500,"name":"Domain Adaptation","url":"https://www.academia.edu/Documents/in/Domain_Adaptation"},{"id":952431,"name":"Korean Cognitive Science","url":"https://www.academia.edu/Documents/in/Korean_Cognitive_Science"},{"id":2064421,"name":"Semantic Role Labeling","url":"https://www.academia.edu/Documents/in/Semantic_Role_Labeling"}],"urls":[{"id":28771675,"url":"http://cs.kangwon.ac.kr/~isl/thesis/2%EC%B0%A8%EB%85%84%EB%8F%84%20%EA%B0%95%EC%9B%90%EB%8C%80/%ED%95%9C%EA%B5%AD%EC%96%B4%20%EC%9D%98%EB%AF%B8%EC%97%AD%20%EA%B2%B0%EC%A0%95%EC%9D%84%20%EC%9C%84%ED%95%9C%20Korean%20PropBank%20%ED%99%95%EC%9E%A5%20%EB%B0%8F%20%EB%8F%84%EB%A9%94%EC%9D%B8%20%EC%A0%81%EC%9D%91%20%EA%B8%B0%EC%88%A0%20%EC%A0%81%EC%9A%A9.pdf"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718953"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/86718953/Easy_Data_Augmentation_for_Improved_Malware_Detection_A_Comparative_Study"><img alt="Research paper thumbnail of Easy Data Augmentation for Improved Malware Detection: A Comparative Study" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/86718953/Easy_Data_Augmentation_for_Improved_Malware_Detection_A_Comparative_Study">Easy Data Augmentation for Improved Malware Detection: A Comparative Study</a></div><div class="wp-workCard_item"><span>2021 IEEE International Conference on Big Data and Smart Computing (BigComp)</span><span>, 2021</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Artificial data generation is important for improving research outcomes when using deep learning....</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">Artificial data generation is important for improving research outcomes when using deep learning. As one of the most popular and promising generative models, the variational auto-encoder (VAE) model generates synthetic data for training classifiers more accurately. Artificial data can be generated also via easy data augmentation (EDA) techniques. EDA is a simple method used to boost the performance of text classification tasks, and unlike generative models such as VAE, it does not require model training. Malware detection is a task of determining whether there is malicious software in the host system and diagnosing the type of attack. Without an appropriate amount of training data, the detection efficiency of malicious programs decreases. In this study, EDA was applied to malware detection, and two artificial data generation methods were compared. Using both methods, artificial training data to be used for malware detection were generated, and the long short-term memory recurrent neural network (LSTM RNN) based malware detection classifier was boosted. Experiment results show that when the synthetic malware sample generated by EDA was added to the training data, the accuracy of LSTM RNN classifier improved by 1.76% as compared to the 0.98% improvement by VAE. In addition, EDA could generate malware training data, without requiring a separate training process, 10 times faster than VAE. Further, we performed extensive ablation studies conducted and suggested parameters for practical use.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718953"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718953"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718953; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718953]").text(description); $(".js-view-count[data-work-id=86718953]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718953; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718953']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718953, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=86718953]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718953,"title":"Easy Data Augmentation for Improved Malware Detection: A Comparative Study","translated_title":"","metadata":{"abstract":"Artificial data generation is important for improving research outcomes when using deep learning. As one of the most popular and promising generative models, the variational auto-encoder (VAE) model generates synthetic data for training classifiers more accurately. Artificial data can be generated also via easy data augmentation (EDA) techniques. EDA is a simple method used to boost the performance of text classification tasks, and unlike generative models such as VAE, it does not require model training. Malware detection is a task of determining whether there is malicious software in the host system and diagnosing the type of attack. Without an appropriate amount of training data, the detection efficiency of malicious programs decreases. In this study, EDA was applied to malware detection, and two artificial data generation methods were compared. Using both methods, artificial training data to be used for malware detection were generated, and the long short-term memory recurrent neural network (LSTM RNN) based malware detection classifier was boosted. Experiment results show that when the synthetic malware sample generated by EDA was added to the training data, the accuracy of LSTM RNN classifier improved by 1.76% as compared to the 0.98% improvement by VAE. In addition, EDA could generate malware training data, without requiring a separate training process, 10 times faster than VAE. Further, we performed extensive ablation studies conducted and suggested parameters for practical use.","publisher":"IEEE","publication_date":{"day":null,"month":null,"year":2021,"errors":{}},"publication_name":"2021 IEEE International Conference on Big Data and Smart Computing (BigComp)"},"translated_abstract":"Artificial data generation is important for improving research outcomes when using deep learning. As one of the most popular and promising generative models, the variational auto-encoder (VAE) model generates synthetic data for training classifiers more accurately. Artificial data can be generated also via easy data augmentation (EDA) techniques. EDA is a simple method used to boost the performance of text classification tasks, and unlike generative models such as VAE, it does not require model training. Malware detection is a task of determining whether there is malicious software in the host system and diagnosing the type of attack. Without an appropriate amount of training data, the detection efficiency of malicious programs decreases. In this study, EDA was applied to malware detection, and two artificial data generation methods were compared. Using both methods, artificial training data to be used for malware detection were generated, and the long short-term memory recurrent neural network (LSTM RNN) based malware detection classifier was boosted. Experiment results show that when the synthetic malware sample generated by EDA was added to the training data, the accuracy of LSTM RNN classifier improved by 1.76% as compared to the 0.98% improvement by VAE. In addition, EDA could generate malware training data, without requiring a separate training process, 10 times faster than VAE. Further, we performed extensive ablation studies conducted and suggested parameters for practical use.","internal_url":"https://www.academia.edu/86718953/Easy_Data_Augmentation_for_Improved_Malware_Detection_A_Comparative_Study","translated_internal_url":"","created_at":"2022-09-15T19:08:50.721-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Easy_Data_Augmentation_for_Improved_Malware_Detection_A_Comparative_Study","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":50154,"name":"Malware","url":"https://www.academia.edu/Documents/in/Malware"}],"urls":[{"id":23885657,"url":"http://xplorestaging.ieee.org/ielx7/9373068/9373070/09373283.pdf?arnumber=9373283"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718952"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/86718952/Korean_Text_Summarization_using_MASS_with_Relative_Position_Representation"><img alt="Research paper thumbnail of Korean Text Summarization using MASS with Relative Position Representation" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/86718952/Korean_Text_Summarization_using_MASS_with_Relative_Position_Representation">Korean Text Summarization using MASS with Relative Position Representation</a></div><div class="wp-workCard_item"><span>Journal of KIISE</span><span>, 2020</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718952"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718952"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718952; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718952]").text(description); $(".js-view-count[data-work-id=86718952]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718952; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718952']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718952, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=86718952]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718952,"title":"Korean Text Summarization using MASS with Relative Position Representation","translated_title":"","metadata":{"publisher":"Korean Institute of Information Scientists and Engineers","publication_date":{"day":null,"month":null,"year":2020,"errors":{}},"publication_name":"Journal of KIISE"},"translated_abstract":null,"internal_url":"https://www.academia.edu/86718952/Korean_Text_Summarization_using_MASS_with_Relative_Position_Representation","translated_internal_url":"","created_at":"2022-09-15T19:08:50.548-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Korean_Text_Summarization_using_MASS_with_Relative_Position_Representation","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":1725616,"name":"Automatic Summarization","url":"https://www.academia.edu/Documents/in/Automatic_Summarization"},{"id":1763882,"name":"Representation Politics","url":"https://www.academia.edu/Documents/in/Representation_Politics"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718951"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/86718951/Named_Entity_Recognition_with_Structural_SVMs_and_Pegasos_algorithm"><img alt="Research paper thumbnail of Named Entity Recognition with Structural SVMs and Pegasos algorithm" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/86718951/Named_Entity_Recognition_with_Structural_SVMs_and_Pegasos_algorithm">Named Entity Recognition with Structural SVMs and Pegasos algorithm</a></div><div class="wp-workCard_item"><span>Korean Journal of Cognitive Science</span><span>, 2010</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Abstract 개체명 인식은 정보 추출의 한 단계로서 정보검색 분야 뿐 아니라 질의응답과 요약 분야에서 매우 유용하게 사용되고 있다. 본 논문에서는 structural Su...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">Abstract 개체명 인식은 정보 추출의 한 단계로서 정보검색 분야 뿐 아니라 질의응답과 요약 분야에서 매우 유용하게 사용되고 있다. 본 논문에서는 structural Support Vector Machines (structural SVMs) 및 수정된 Pegasos 알고리즘을 이용한 한국어 개체명 인식 시스템에 ...</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718951"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718951"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718951; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718951]").text(description); $(".js-view-count[data-work-id=86718951]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718951; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718951']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718951, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=86718951]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718951,"title":"Named Entity Recognition with Structural SVMs and Pegasos algorithm","translated_title":"","metadata":{"abstract":"Abstract 개체명 인식은 정보 추출의 한 단계로서 정보검색 분야 뿐 아니라 질의응답과 요약 분야에서 매우 유용하게 사용되고 있다. 본 논문에서는 structural Support Vector Machines (structural SVMs) 및 수정된 Pegasos 알고리즘을 이용한 한국어 개체명 인식 시스템에 ...","publisher":"The Korean Society for Cognitive Science","publication_date":{"day":null,"month":null,"year":2010,"errors":{}},"publication_name":"Korean Journal of Cognitive Science"},"translated_abstract":"Abstract 개체명 인식은 정보 추출의 한 단계로서 정보검색 분야 뿐 아니라 질의응답과 요약 분야에서 매우 유용하게 사용되고 있다. 본 논문에서는 structural Support Vector Machines (structural SVMs) 및 수정된 Pegasos 알고리즘을 이용한 한국어 개체명 인식 시스템에 ...","internal_url":"https://www.academia.edu/86718951/Named_Entity_Recognition_with_Structural_SVMs_and_Pegasos_algorithm","translated_internal_url":"","created_at":"2022-09-15T19:08:50.374-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Named_Entity_Recognition_with_Structural_SVMs_and_Pegasos_algorithm","translated_slug":"","page_count":null,"language":"ko","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":191289,"name":"Support vector machine","url":"https://www.academia.edu/Documents/in/Support_vector_machine"},{"id":952431,"name":"Korean Cognitive Science","url":"https://www.academia.edu/Documents/in/Korean_Cognitive_Science"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718950"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/86718950/Fine_grained_named_entity_recognition_and_relation_extraction_for_question_answering"><img alt="Research paper thumbnail of Fine-grained named entity recognition and relation extraction for question answering" class="work-thumbnail" src="https://attachments.academia-assets.com/91107832/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/86718950/Fine_grained_named_entity_recognition_and_relation_extraction_for_question_answering">Fine-grained named entity recognition and relation extraction for question answering</a></div><div class="wp-workCard_item"><span>Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '07</span><span>, 2007</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="c48c7f3d024452c033c1d0d6718bedb6" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":91107832,"asset_id":86718950,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/91107832/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718950"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718950"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718950; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718950]").text(description); $(".js-view-count[data-work-id=86718950]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718950; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718950']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718950, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "c48c7f3d024452c033c1d0d6718bedb6" } } $('.js-work-strip[data-work-id=86718950]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718950,"title":"Fine-grained named entity recognition and relation extraction for question answering","translated_title":"","metadata":{"publisher":"ACM Press","publication_date":{"day":null,"month":null,"year":2007,"errors":{}},"publication_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '07"},"translated_abstract":null,"internal_url":"https://www.academia.edu/86718950/Fine_grained_named_entity_recognition_and_relation_extraction_for_question_answering","translated_internal_url":"","created_at":"2022-09-15T19:08:50.140-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":91107832,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107832/thumbnails/1.jpg","file_name":"pryo4wzei8b0qs9hjaxidjg7xn6lmdvf.pdf","download_url":"https://www.academia.edu/attachments/91107832/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Fine_grained_named_entity_recognition_an.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107832/pryo4wzei8b0qs9hjaxidjg7xn6lmdvf-libre.pdf?1663299299=\u0026response-content-disposition=attachment%3B+filename%3DFine_grained_named_entity_recognition_an.pdf\u0026Expires=1733028036\u0026Signature=UT59MfW-vV9p3EphGEHlu5wZqucSyUB~g039kymEfTaT7Hlm8KbSDfErHHsZJV7cLT-2xfV1UPw95vsRYYZFR7h9lqHXN2-xVGf1SMSxAdWSKEHZqh4ecWI4Fh2Vv3VpXw8s06TyZcid3PAVLil3H3L4-UYLFcRHMb4OfXDT26UxfUP4XawXa~VqPV778Speafw~IOLoslHvkcNV-7hiAdO2ptdQZFL6DG8I9jaLbzr8~I5P9IIsww1b0EPKOsgmNxpdtiEv4JkOKTMIVMiXJaXeNZJUnfDcWADMQh1TvQIOuUQuR1ixDtRl5geJtbGLX3hSxbqCDoguy6V2EkVupg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Fine_grained_named_entity_recognition_and_relation_extraction_for_question_answering","translated_slug":"","page_count":2,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":91107832,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107832/thumbnails/1.jpg","file_name":"pryo4wzei8b0qs9hjaxidjg7xn6lmdvf.pdf","download_url":"https://www.academia.edu/attachments/91107832/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Fine_grained_named_entity_recognition_an.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107832/pryo4wzei8b0qs9hjaxidjg7xn6lmdvf-libre.pdf?1663299299=\u0026response-content-disposition=attachment%3B+filename%3DFine_grained_named_entity_recognition_an.pdf\u0026Expires=1733028036\u0026Signature=UT59MfW-vV9p3EphGEHlu5wZqucSyUB~g039kymEfTaT7Hlm8KbSDfErHHsZJV7cLT-2xfV1UPw95vsRYYZFR7h9lqHXN2-xVGf1SMSxAdWSKEHZqh4ecWI4Fh2Vv3VpXw8s06TyZcid3PAVLil3H3L4-UYLFcRHMb4OfXDT26UxfUP4XawXa~VqPV778Speafw~IOLoslHvkcNV-7hiAdO2ptdQZFL6DG8I9jaLbzr8~I5P9IIsww1b0EPKOsgmNxpdtiEv4JkOKTMIVMiXJaXeNZJUnfDcWADMQh1TvQIOuUQuR1ixDtRl5geJtbGLX3hSxbqCDoguy6V2EkVupg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":29205,"name":"Named Entity Recognition","url":"https://www.academia.edu/Documents/in/Named_Entity_Recognition"},{"id":184950,"name":"Question Answering","url":"https://www.academia.edu/Documents/in/Question_Answering"},{"id":188880,"name":"Relation Extraction","url":"https://www.academia.edu/Documents/in/Relation_Extraction"}],"urls":[{"id":23885656,"url":"http://dl.acm.org/ft_gateway.cfm?id=1277915\u0026amp%3Bftid=431583\u0026amp%3Bdwn=1"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718949"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/86718949/Information_gain_and_divergence_based_feature_selection_for_machine_learning_based_text_categorization"><img alt="Research paper thumbnail of Information gain and divergence-based feature selection for machine learning-based text categorization" class="work-thumbnail" src="https://attachments.academia-assets.com/91107834/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/86718949/Information_gain_and_divergence_based_feature_selection_for_machine_learning_based_text_categorization">Information gain and divergence-based feature selection for machine learning-based text categorization</a></div><div class="wp-workCard_item"><span>Information Processing &amp; Management</span><span>, 2006</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="520d8e795f57c2cfd42fb479950b0788" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":91107834,"asset_id":86718949,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/91107834/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718949"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718949"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718949; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718949]").text(description); $(".js-view-count[data-work-id=86718949]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718949; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718949']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718949, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "520d8e795f57c2cfd42fb479950b0788" } } $('.js-work-strip[data-work-id=86718949]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718949,"title":"Information gain and divergence-based feature selection for machine learning-based text categorization","translated_title":"","metadata":{"publisher":"Elsevier BV","grobid_abstract":"Most previous works of feature selection emphasized only the reduction of high dimensionality of the feature space. But in cases where many features are highly redundant with each other, we must utilize other means, for example, more complex dependence models such as Bayesian network classifiers. In this paper, we introduce a new information gain and divergence-based feature selection method for statistical machine learning-based text categorization without relying on more complex dependence models. Our feature selection method strives to reduce redundancy between features while maintaining information gain in selecting appropriate features for text categorization. Empirical results are given on a number of dataset, showing that our feature selection method is more effective than Koller and SahamiÕs method [Koller, D., \u0026 Sahami, M. (1996). Toward optimal feature selection. In Proceedings of ICML-96, 13th international conference on machine learning], which is one of greedy feature selection methods, and conventional information gain which is commonly used in feature selection for text categorization. Moreover, our feature selection method sometimes produces more improvements of conventional machine learning algorithms over support vector machines which are known to give the best classification accuracy.","publication_date":{"day":null,"month":null,"year":2006,"errors":{}},"publication_name":"Information Processing \u0026amp; Management","grobid_abstract_attachment_id":91107834},"translated_abstract":null,"internal_url":"https://www.academia.edu/86718949/Information_gain_and_divergence_based_feature_selection_for_machine_learning_based_text_categorization","translated_internal_url":"","created_at":"2022-09-15T19:08:49.815-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":91107834,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107834/thumbnails/1.jpg","file_name":"feature_20selection.pdf","download_url":"https://www.academia.edu/attachments/91107834/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Information_gain_and_divergence_based_fe.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107834/feature_20selection-libre.pdf?1663299302=\u0026response-content-disposition=attachment%3B+filename%3DInformation_gain_and_divergence_based_fe.pdf\u0026Expires=1733028036\u0026Signature=f2e-DctCwrgrhFJffc8YvacZ60WotQxjtnMkmYNZn8zNXK2gg5DuJozm906scYd~hcbaJgz9ygVG6py3gWXKU88B~5-hMwmg4XzvJiIfSHD2feZGKKsXSlJ9NIfGzKurBQSd6qVLCWIZFdZWkRYFPjdplurxefhWUwyri28KOlAOT7~X1EvC4QdcTroyIU0CSLareGcHg99gfH~iDorWey8PJtMYwmwBDMUk62Cd810ypPhY1l8gilhGtHWO~JDLqR7m04UfEM8kUPvBCsxy4bB3rebrs~xnwBMX-~2UUL~KbgoVwhT9fr742ypNmA9svwK9K4N5xQmoy5awtc9VAg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Information_gain_and_divergence_based_feature_selection_for_machine_learning_based_text_categorization","translated_slug":"","page_count":11,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":91107834,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107834/thumbnails/1.jpg","file_name":"feature_20selection.pdf","download_url":"https://www.academia.edu/attachments/91107834/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Information_gain_and_divergence_based_fe.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107834/feature_20selection-libre.pdf?1663299302=\u0026response-content-disposition=attachment%3B+filename%3DInformation_gain_and_divergence_based_fe.pdf\u0026Expires=1733028036\u0026Signature=f2e-DctCwrgrhFJffc8YvacZ60WotQxjtnMkmYNZn8zNXK2gg5DuJozm906scYd~hcbaJgz9ygVG6py3gWXKU88B~5-hMwmg4XzvJiIfSHD2feZGKKsXSlJ9NIfGzKurBQSd6qVLCWIZFdZWkRYFPjdplurxefhWUwyri28KOlAOT7~X1EvC4QdcTroyIU0CSLareGcHg99gfH~iDorWey8PJtMYwmwBDMUk62Cd810ypPhY1l8gilhGtHWO~JDLqR7m04UfEM8kUPvBCsxy4bB3rebrs~xnwBMX-~2UUL~KbgoVwhT9fr742ypNmA9svwK9K4N5xQmoy5awtc9VAg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":37,"name":"Information Systems","url":"https://www.academia.edu/Documents/in/Information_Systems"},{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":2008,"name":"Machine Learning","url":"https://www.academia.edu/Documents/in/Machine_Learning"},{"id":18573,"name":"Categorization","url":"https://www.academia.edu/Documents/in/Categorization"},{"id":43619,"name":"Feature Selection","url":"https://www.academia.edu/Documents/in/Feature_Selection"},{"id":47555,"name":"Dimensionality Reduction","url":"https://www.academia.edu/Documents/in/Dimensionality_Reduction"},{"id":59587,"name":"Library and Information Studies","url":"https://www.academia.edu/Documents/in/Library_and_Information_Studies"},{"id":124340,"name":"Text Categorization","url":"https://www.academia.edu/Documents/in/Text_Categorization"}],"urls":[{"id":23885655,"url":"https://api.elsevier.com/content/article/PII:S0306457304000962?httpAccept=text/xml"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718948"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/86718948/A_Multi_Strategic_Concept_Spotting_Approach_for_Robust_Understanding_of_Spoken_Korean"><img alt="Research paper thumbnail of A Multi-Strategic Concept-Spotting Approach for Robust Understanding of Spoken Korean" class="work-thumbnail" src="https://attachments.academia-assets.com/91107831/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/86718948/A_Multi_Strategic_Concept_Spotting_Approach_for_Robust_Understanding_of_Spoken_Korean">A Multi-Strategic Concept-Spotting Approach for Robust Understanding of Spoken Korean</a></div><div class="wp-workCard_item"><span>ETRI Journal</span><span>, 2007</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="aedf55a04090765162d103090b8d11ab" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":91107831,"asset_id":86718948,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/91107831/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718948"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718948"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718948; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718948]").text(description); $(".js-view-count[data-work-id=86718948]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718948; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718948']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718948, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "aedf55a04090765162d103090b8d11ab" } } $('.js-work-strip[data-work-id=86718948]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718948,"title":"A Multi-Strategic Concept-Spotting Approach for Robust Understanding of Spoken Korean","translated_title":"","metadata":{"publisher":"Wiley-Blackwell","publication_date":{"day":null,"month":null,"year":2007,"errors":{}},"publication_name":"ETRI Journal"},"translated_abstract":null,"internal_url":"https://www.academia.edu/86718948/A_Multi_Strategic_Concept_Spotting_Approach_for_Robust_Understanding_of_Spoken_Korean","translated_internal_url":"","created_at":"2022-09-15T19:08:49.656-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":91107831,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107831/thumbnails/1.jpg","file_name":"ff01038f3ce5177c98ccc058160dcfe0e08e.pdf","download_url":"https://www.academia.edu/attachments/91107831/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"A_Multi_Strategic_Concept_Spotting_Appro.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107831/ff01038f3ce5177c98ccc058160dcfe0e08e-libre.pdf?1663299302=\u0026response-content-disposition=attachment%3B+filename%3DA_Multi_Strategic_Concept_Spotting_Appro.pdf\u0026Expires=1733028036\u0026Signature=KPmd4kdb2dJTIK5QqelGpRhEZBfbqbkHK~DBAfYjK8QVV0FsWbaw6K8ANa0jPYUmGeSYhobEzGSpPTGfkhJ6AkQjLZ3vSjJNgxNrx8oZwSARn9EtYRzhsUj3kE-n4fM3QlD01bLVHVvlA7cORpqjIj8KBfilcc4oxwBI8mD9~kzxPJe5PBoR3oBNuuMqP-MvkLZmeRLj5qLhpj7Ih2LVrvBdisaKprSqK6cNB8V5fzk4tNj8rBXIcoQFrCxS6mQv13OetQlzlKmFn0ZNDdwmUJDDavC7yXMQlSOAlE6bTFNUu-p~cMs4ipKekU6qjuBr4hc58UUXPgiOdxYF329H7Q__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"A_Multi_Strategic_Concept_Spotting_Approach_for_Robust_Understanding_of_Spoken_Korean","translated_slug":"","page_count":10,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":91107831,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107831/thumbnails/1.jpg","file_name":"ff01038f3ce5177c98ccc058160dcfe0e08e.pdf","download_url":"https://www.academia.edu/attachments/91107831/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"A_Multi_Strategic_Concept_Spotting_Appro.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107831/ff01038f3ce5177c98ccc058160dcfe0e08e-libre.pdf?1663299302=\u0026response-content-disposition=attachment%3B+filename%3DA_Multi_Strategic_Concept_Spotting_Appro.pdf\u0026Expires=1733028036\u0026Signature=KPmd4kdb2dJTIK5QqelGpRhEZBfbqbkHK~DBAfYjK8QVV0FsWbaw6K8ANa0jPYUmGeSYhobEzGSpPTGfkhJ6AkQjLZ3vSjJNgxNrx8oZwSARn9EtYRzhsUj3kE-n4fM3QlD01bLVHVvlA7cORpqjIj8KBfilcc4oxwBI8mD9~kzxPJe5PBoR3oBNuuMqP-MvkLZmeRLj5qLhpj7Ih2LVrvBdisaKprSqK6cNB8V5fzk4tNj8rBXIcoQFrCxS6mQv13OetQlzlKmFn0ZNDdwmUJDDavC7yXMQlSOAlE6bTFNUu-p~cMs4ipKekU6qjuBr4hc58UUXPgiOdxYF329H7Q__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":37,"name":"Information Systems","url":"https://www.academia.edu/Documents/in/Information_Systems"},{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":11128,"name":"Information Extraction","url":"https://www.academia.edu/Documents/in/Information_Extraction"},{"id":102864,"name":"Spoken language","url":"https://www.academia.edu/Documents/in/Spoken_language"},{"id":119709,"name":"Spontaneous speech","url":"https://www.academia.edu/Documents/in/Spontaneous_speech"},{"id":151727,"name":"Keyword Spotting","url":"https://www.academia.edu/Documents/in/Keyword_Spotting"},{"id":1237788,"name":"Electrical And Electronic Engineering","url":"https://www.academia.edu/Documents/in/Electrical_And_Electronic_Engineering"},{"id":1763882,"name":"Representation Politics","url":"https://www.academia.edu/Documents/in/Representation_Politics"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718947"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/86718947/Dependency_Structure_Applied_to_Language_Modeling_for_Information_Retrieval"><img alt="Research paper thumbnail of Dependency Structure Applied to Language Modeling for Information Retrieval" class="work-thumbnail" src="https://attachments.academia-assets.com/91107833/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/86718947/Dependency_Structure_Applied_to_Language_Modeling_for_Information_Retrieval">Dependency Structure Applied to Language Modeling for Information Retrieval</a></div><div class="wp-workCard_item"><span>ETRI Journal</span><span>, 2006</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="0023d0f23b53acfbd4066798fd36ff95" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":91107833,"asset_id":86718947,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/91107833/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718947"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718947"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718947; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718947]").text(description); $(".js-view-count[data-work-id=86718947]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718947; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718947']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718947, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "0023d0f23b53acfbd4066798fd36ff95" } } $('.js-work-strip[data-work-id=86718947]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718947,"title":"Dependency Structure Applied to Language Modeling for Information Retrieval","translated_title":"","metadata":{"publisher":"Wiley","grobid_abstract":"In this paper, we propose a new language model, namely, a dependency structure language model, for information retrieval to compensate for the weaknesses of unigram and bigram language models. The dependency structure language model is based on the first-order dependency model and the dependency parse tree generated by a linguistic parser. So, long-distance dependencies can be naturally captured by the dependency structure language model. We carried out extensive experiments to verify the proposed model, where the dependency structure model gives a better performance than recently proposed language models and the Okapi BM25 method, and the dependency structure is more effective than unigram and bigram in language modeling for information retrieval.","publication_date":{"day":null,"month":null,"year":2006,"errors":{}},"publication_name":"ETRI Journal","grobid_abstract_attachment_id":91107833},"translated_abstract":null,"internal_url":"https://www.academia.edu/86718947/Dependency_Structure_Applied_to_Language_Modeling_for_Information_Retrieval","translated_internal_url":"","created_at":"2022-09-15T19:08:49.436-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":91107833,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107833/thumbnails/1.jpg","file_name":"HJTODO_2006_v28n3_337.pdf","download_url":"https://www.academia.edu/attachments/91107833/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Dependency_Structure_Applied_to_Language.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107833/HJTODO_2006_v28n3_337-libre.pdf?1663299307=\u0026response-content-disposition=attachment%3B+filename%3DDependency_Structure_Applied_to_Language.pdf\u0026Expires=1733028036\u0026Signature=Rv0OlY2TOJSUBiLtZeX2a~IhsiMWhZ2tVaPs3rYVwI350-~S7eNmuqR0iQ615zKNHs-~HsSeV3V6VxEpD-hCJdFXausMHMfO89-gJBTp3wKSjh8cyUGLmQ0ZL817DlBclYSxNrPZhqPu3QJ4PTOXmL8G5fFTr04~RGwz7H7~u7LfnPEXVVEA-BDfErIGWliw3TS9XRN54u6lQUvI~FpJ8Iun8hNBITD--9cLchDTDMO8UJTitp5b5mt0y98YBwYwOKAqoKSjvH01j0Yqz7hvUwCAi3~0nmWZP8Oc~ezy~35oyj7PP3XhtgiOf00zoSdkcdcHqsoUFtCcvUi~fBEGow__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Dependency_Structure_Applied_to_Language_Modeling_for_Information_Retrieval","translated_slug":"","page_count":10,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":91107833,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107833/thumbnails/1.jpg","file_name":"HJTODO_2006_v28n3_337.pdf","download_url":"https://www.academia.edu/attachments/91107833/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Dependency_Structure_Applied_to_Language.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107833/HJTODO_2006_v28n3_337-libre.pdf?1663299307=\u0026response-content-disposition=attachment%3B+filename%3DDependency_Structure_Applied_to_Language.pdf\u0026Expires=1733028036\u0026Signature=Rv0OlY2TOJSUBiLtZeX2a~IhsiMWhZ2tVaPs3rYVwI350-~S7eNmuqR0iQ615zKNHs-~HsSeV3V6VxEpD-hCJdFXausMHMfO89-gJBTp3wKSjh8cyUGLmQ0ZL817DlBclYSxNrPZhqPu3QJ4PTOXmL8G5fFTr04~RGwz7H7~u7LfnPEXVVEA-BDfErIGWliw3TS9XRN54u6lQUvI~FpJ8Iun8hNBITD--9cLchDTDMO8UJTitp5b5mt0y98YBwYwOKAqoKSjvH01j0Yqz7hvUwCAi3~0nmWZP8Oc~ezy~35oyj7PP3XhtgiOf00zoSdkcdcHqsoUFtCcvUi~fBEGow__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":37,"name":"Information Systems","url":"https://www.academia.edu/Documents/in/Information_Systems"},{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":1237788,"name":"Electrical And Electronic Engineering","url":"https://www.academia.edu/Documents/in/Electrical_And_Electronic_Engineering"}],"urls":[{"id":23885654,"url":"https://etrij.etri.re.kr/etrij/journal/getPublishedPaperFile.do?fileId=SPF-1149841527877"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718918"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/86718918/Net_Korean_Machine_Reading_Comprehension_using_SRU_based_Sentence_and_Self_Matching_Networks"><img alt="Research paper thumbnail of Net : Korean Machine Reading Comprehension using SRU-based Sentence and Self Matching Networks" class="work-thumbnail" src="https://attachments.academia-assets.com/91107777/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/86718918/Net_Korean_Machine_Reading_Comprehension_using_SRU_based_Sentence_and_Self_Matching_Networks">Net : Korean Machine Reading Comprehension using SRU-based Sentence and Self Matching Networks</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">셋에서 기존의 S-Net보다 우수한 (dev) EM 70.08%, F1 81.78%, (test) EM 69.43%, F1 81.53%의 성능을 보였다. 1. 서 론 기계 독...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">셋에서 기존의 S-Net보다 우수한 (dev) EM 70.08%, F1 81.78%, (test) EM 69.43%, F1 81.53%의 성능을 보였다. 1. 서 론 기계 독해를 이용한 질의 응답(Question Answering)은 페이스북 bAbi task의 CBT와 같이 주어진 문맥에서 빈칸을 채우는 cloze 스타일과 주 어진 문맥에서 정답이 포함된 문장을 찾는 WikiQA, 주어진 문맥에서 정답의 시작과 끝 경계를 찾는 스탠포드의 SQuAD등과 같은 문제들로 나뉘며, 좀더 복합적인 문제로 마이크로소프트의 MS-MARCO가 있다 [1, 2, 3, 4]. 위와 같은 문제를 해결하기 위해서는 기계가 주어진 문맥을 이해하고 문맥 내에서 정답을 찾아야 하는데, 이처럼 기계가 주어진 문 장을 이해하는 것을 기계 독해(Machine Reading Comprehension)라 한 다. 예를 들어, 기계 독해 시스템은 “국내 건조기 시장 점유율 1위 누구 야?”와 같은 질문에 대하여, 문맥 “2004년 건조기 시장에 ... 의류 건조 기 중 LG전자는 점유율 77.4%로 1위를 차지했다.”를 이해하고, 해당 문맥 내에서 정답 “LG전자”를 찾아 출력한다. 기계 독해 문제를 해결하기 위하여 S2-Net, DrQA, fastQA, RNet, Bi-Directional Flow (BiDAF) 등[5-9]과 같은 end-to-end 딥 러 닝 모델들이 연구되고 있으며, 이러한 모델들은 주어진 질문과 문 맥에 대하여 매칭과 인코딩을 수행하고, 질문과 문맥을 매칭하고, 어텐션 매커니즘(attention mechanism)[10]을 기반으로 한 포인터 네트워크(Pointer Networks)[11]로 질문과 유사한 정답의 경계 인 덱스(즉, 정답의 시작과 끝 위치)를 출력한다. 본 논문의 선행 연 구인 S2-Net은 한국어 기계 독해 데이터셋인 MindsMRC에서 질 의응답을 적용하였으며, 이때 주어진 하나의 문단은 여러 문장으</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="c287d5654c30bdae68f21c5f0f25a99e" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":91107777,"asset_id":86718918,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/91107777/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718918"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718918"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718918; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718918]").text(description); $(".js-view-count[data-work-id=86718918]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718918; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718918']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718918, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "c287d5654c30bdae68f21c5f0f25a99e" } } $('.js-work-strip[data-work-id=86718918]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718918,"title":"Net : Korean Machine Reading Comprehension using SRU-based Sentence and Self Matching Networks","translated_title":"","metadata":{"abstract":"셋에서 기존의 S-Net보다 우수한 (dev) EM 70.08%, F1 81.78%, (test) EM 69.43%, F1 81.53%의 성능을 보였다. 1. 서 론 기계 독해를 이용한 질의 응답(Question Answering)은 페이스북 bAbi task의 CBT와 같이 주어진 문맥에서 빈칸을 채우는 cloze 스타일과 주 어진 문맥에서 정답이 포함된 문장을 찾는 WikiQA, 주어진 문맥에서 정답의 시작과 끝 경계를 찾는 스탠포드의 SQuAD등과 같은 문제들로 나뉘며, 좀더 복합적인 문제로 마이크로소프트의 MS-MARCO가 있다 [1, 2, 3, 4]. 위와 같은 문제를 해결하기 위해서는 기계가 주어진 문맥을 이해하고 문맥 내에서 정답을 찾아야 하는데, 이처럼 기계가 주어진 문 장을 이해하는 것을 기계 독해(Machine Reading Comprehension)라 한 다. 예를 들어, 기계 독해 시스템은 “국내 건조기 시장 점유율 1위 누구 야?”와 같은 질문에 대하여, 문맥 “2004년 건조기 시장에 ... 의류 건조 기 중 LG전자는 점유율 77.4%로 1위를 차지했다.”를 이해하고, 해당 문맥 내에서 정답 “LG전자”를 찾아 출력한다. 기계 독해 문제를 해결하기 위하여 S2-Net, DrQA, fastQA, RNet, Bi-Directional Flow (BiDAF) 등[5-9]과 같은 end-to-end 딥 러 닝 모델들이 연구되고 있으며, 이러한 모델들은 주어진 질문과 문 맥에 대하여 매칭과 인코딩을 수행하고, 질문과 문맥을 매칭하고, 어텐션 매커니즘(attention mechanism)[10]을 기반으로 한 포인터 네트워크(Pointer Networks)[11]로 질문과 유사한 정답의 경계 인 덱스(즉, 정답의 시작과 끝 위치)를 출력한다. 본 논문의 선행 연 구인 S2-Net은 한국어 기계 독해 데이터셋인 MindsMRC에서 질 의응답을 적용하였으며, 이때 주어진 하나의 문단은 여러 문장으","publication_date":{"day":null,"month":null,"year":2017,"errors":{}}},"translated_abstract":"셋에서 기존의 S-Net보다 우수한 (dev) EM 70.08%, F1 81.78%, (test) EM 69.43%, F1 81.53%의 성능을 보였다. 1. 서 론 기계 독해를 이용한 질의 응답(Question Answering)은 페이스북 bAbi task의 CBT와 같이 주어진 문맥에서 빈칸을 채우는 cloze 스타일과 주 어진 문맥에서 정답이 포함된 문장을 찾는 WikiQA, 주어진 문맥에서 정답의 시작과 끝 경계를 찾는 스탠포드의 SQuAD등과 같은 문제들로 나뉘며, 좀더 복합적인 문제로 마이크로소프트의 MS-MARCO가 있다 [1, 2, 3, 4]. 위와 같은 문제를 해결하기 위해서는 기계가 주어진 문맥을 이해하고 문맥 내에서 정답을 찾아야 하는데, 이처럼 기계가 주어진 문 장을 이해하는 것을 기계 독해(Machine Reading Comprehension)라 한 다. 예를 들어, 기계 독해 시스템은 “국내 건조기 시장 점유율 1위 누구 야?”와 같은 질문에 대하여, 문맥 “2004년 건조기 시장에 ... 의류 건조 기 중 LG전자는 점유율 77.4%로 1위를 차지했다.”를 이해하고, 해당 문맥 내에서 정답 “LG전자”를 찾아 출력한다. 기계 독해 문제를 해결하기 위하여 S2-Net, DrQA, fastQA, RNet, Bi-Directional Flow (BiDAF) 등[5-9]과 같은 end-to-end 딥 러 닝 모델들이 연구되고 있으며, 이러한 모델들은 주어진 질문과 문 맥에 대하여 매칭과 인코딩을 수행하고, 질문과 문맥을 매칭하고, 어텐션 매커니즘(attention mechanism)[10]을 기반으로 한 포인터 네트워크(Pointer Networks)[11]로 질문과 유사한 정답의 경계 인 덱스(즉, 정답의 시작과 끝 위치)를 출력한다. 본 논문의 선행 연 구인 S2-Net은 한국어 기계 독해 데이터셋인 MindsMRC에서 질 의응답을 적용하였으며, 이때 주어진 하나의 문단은 여러 문장으","internal_url":"https://www.academia.edu/86718918/Net_Korean_Machine_Reading_Comprehension_using_SRU_based_Sentence_and_Self_Matching_Networks","translated_internal_url":"","created_at":"2022-09-15T19:07:31.360-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":91107777,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107777/thumbnails/1.jpg","file_name":"SRU_20_EA_B8_B0_EB_B0_98_20_EB_AC_B8_EC_9E_A5_20_EB_B0_8F_20_EC_85_80_ED_94_84_20_EB_A7_A4_EC_B9_AD_20_EB_84_A4_ED_8A_B8_EC_9B_8C_ED_81_.pdf","download_url":"https://www.academia.edu/attachments/91107777/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Net_Korean_Machine_Reading_Comprehension.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107777/SRU_20_EA_B8_B0_EB_B0_98_20_EB_AC_B8_EC_9E_A5_20_EB_B0_8F_20_EC_85_80_ED_94_84_20_EB_A7_A4_EC_B9_AD_20_EB_84_A4_ED_8A_B8_EC_9B_8C_ED_81_-libre.pdf?1663299315=\u0026response-content-disposition=attachment%3B+filename%3DNet_Korean_Machine_Reading_Comprehension.pdf\u0026Expires=1732979528\u0026Signature=F7m3odfyZT3dQFGKYcP3bgC-8~W-a9g0HR1eSm9LkaweSUlPpgWBWW9Hjl1dbl7NfDf4lZ0DuDOelLshXSlMl5xTSe0g~ZrdjDe0x5zR-nCUKLDVz12C1xDQMCtQ~VD28Q3Ec8tYuvexWQlEN1YabSHuBVfbHux2ljdzVhJvtqZIzkP3ZN0D2eoqc13lr7A4DAfSJ4wwF37otar42f6EKfdB88rmNzFjfO2c0HOjAVC4w6iY3wiNNDpyy8IgZkKYl2TAiSJ8tHEp2s8fSX1eG1IeGggCe-XEhkf0y8o66fxD-UaBnKcnAExVqRXEyZf5-XZ1Ln5OZ3~9bJwmbVnrBQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Net_Korean_Machine_Reading_Comprehension_using_SRU_based_Sentence_and_Self_Matching_Networks","translated_slug":"","page_count":3,"language":"ko","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":91107777,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107777/thumbnails/1.jpg","file_name":"SRU_20_EA_B8_B0_EB_B0_98_20_EB_AC_B8_EC_9E_A5_20_EB_B0_8F_20_EC_85_80_ED_94_84_20_EB_A7_A4_EC_B9_AD_20_EB_84_A4_ED_8A_B8_EC_9B_8C_ED_81_.pdf","download_url":"https://www.academia.edu/attachments/91107777/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Net_Korean_Machine_Reading_Comprehension.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107777/SRU_20_EA_B8_B0_EB_B0_98_20_EB_AC_B8_EC_9E_A5_20_EB_B0_8F_20_EC_85_80_ED_94_84_20_EB_A7_A4_EC_B9_AD_20_EB_84_A4_ED_8A_B8_EC_9B_8C_ED_81_-libre.pdf?1663299315=\u0026response-content-disposition=attachment%3B+filename%3DNet_Korean_Machine_Reading_Comprehension.pdf\u0026Expires=1732979528\u0026Signature=F7m3odfyZT3dQFGKYcP3bgC-8~W-a9g0HR1eSm9LkaweSUlPpgWBWW9Hjl1dbl7NfDf4lZ0DuDOelLshXSlMl5xTSe0g~ZrdjDe0x5zR-nCUKLDVz12C1xDQMCtQ~VD28Q3Ec8tYuvexWQlEN1YabSHuBVfbHux2ljdzVhJvtqZIzkP3ZN0D2eoqc13lr7A4DAfSJ4wwF37otar42f6EKfdB88rmNzFjfO2c0HOjAVC4w6iY3wiNNDpyy8IgZkKYl2TAiSJ8tHEp2s8fSX1eG1IeGggCe-XEhkf0y8o66fxD-UaBnKcnAExVqRXEyZf5-XZ1Ln5OZ3~9bJwmbVnrBQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"},{"id":91107776,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107776/thumbnails/1.jpg","file_name":"SRU_20_EA_B8_B0_EB_B0_98_20_EB_AC_B8_EC_9E_A5_20_EB_B0_8F_20_EC_85_80_ED_94_84_20_EB_A7_A4_EC_B9_AD_20_EB_84_A4_ED_8A_B8_EC_9B_8C_ED_81_.pdf","download_url":"https://www.academia.edu/attachments/91107776/download_file","bulk_download_file_name":"Net_Korean_Machine_Reading_Comprehension.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107776/SRU_20_EA_B8_B0_EB_B0_98_20_EB_AC_B8_EC_9E_A5_20_EB_B0_8F_20_EC_85_80_ED_94_84_20_EB_A7_A4_EC_B9_AD_20_EB_84_A4_ED_8A_B8_EC_9B_8C_ED_81_-libre.pdf?1663299314=\u0026response-content-disposition=attachment%3B+filename%3DNet_Korean_Machine_Reading_Comprehension.pdf\u0026Expires=1732979528\u0026Signature=HGfVD6aYXrQL4jIxRkL5x5XhB3bjNR5kXE2AP2hX73otbeQ5ZBuC2DXFSAeSI9kabsv7XbzlmARXOadh7PZrZHE3F~qT3cW8yOCE~jy0zXomX8bsRbT~0XPAPo9ZsXRtoEe~On~zjEEPopClGGDm5oGjejy9VSmFIdrAWufZFMyLzAYEULP-dgYr~34XLnF1t8xSLfpBvbFC0Niygy3aOupph9oeM~xFBGUH5tQpVOkfYZ469pxaHsl4R6Ux4zecbRdpdXrbq1YErMoSIHIFjVNh~cbq60l5wffyGlvji~exq44OJlz4t4dsA2jsc0xI23JzvVqllEms2O7IrPs2Rg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[],"urls":[{"id":23885638,"url":"http://cs.kangwon.ac.kr/~isl/thesis/%EB%85%BC%EB%AC%B8/SRU%20%EA%B8%B0%EB%B0%98%20%EB%AC%B8%EC%9E%A5%20%EB%B0%8F%20%EC%85%80%ED%94%84%20%EB%A7%A4%EC%B9%AD%20%EB%84%A4%ED%8A%B8%EC%9B%8C%ED%81%AC%EB%A5%BC%20%EC%9D%B4%EC%9A%A9%ED%95%9C%20%ED%95%9C%EA%B5%AD%EC%96%B4%20%EA%B8%B0%EA%B3%84%EB%8F%85%ED%95%B4.pdf"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="82772018"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/82772018/Structural_SVM%EC%9D%84_%EC%9D%B4%EC%9A%A9%ED%95%9C_%ED%95%9C%EA%B5%AD%EC%96%B4_%EB%9D%84%EC%96%B4%EC%93%B0%EA%B8%B0_%EB%B0%8F_%ED%92%88%EC%82%AC_%ED%83%9C%EA%B9%85_%EA%B2%B0%ED%95%A9_%EB%AA%A8%EB%8D%B8_Joint_Models_for_Korean_Word_Spacing_and_POS_Tagging_using_Structural_SVM_"><img alt="Research paper thumbnail of Structural SVM을 이용한 한국어 띄어쓰기 및 품사 태깅 결합 모델 (Joint Models for Korean Word Spacing and POS Tagging using Structural SVM)" class="work-thumbnail" src="https://attachments.academia-assets.com/88368653/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/82772018/Structural_SVM%EC%9D%84_%EC%9D%B4%EC%9A%A9%ED%95%9C_%ED%95%9C%EA%B5%AD%EC%96%B4_%EB%9D%84%EC%96%B4%EC%93%B0%EA%B8%B0_%EB%B0%8F_%ED%92%88%EC%82%AC_%ED%83%9C%EA%B9%85_%EA%B2%B0%ED%95%A9_%EB%AA%A8%EB%8D%B8_Joint_Models_for_Korean_Word_Spacing_and_POS_Tagging_using_Structural_SVM_">Structural SVM을 이용한 한국어 띄어쓰기 및 품사 태깅 결합 모델 (Joint Models for Korean Word Spacing and POS Tagging using Structural SVM)</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Typically, a Korean Part-of-speech (POS) tagger takes the inputs that are produced by a separate ...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">Typically, a Korean Part-of-speech (POS) tagger takes the inputs that are produced by a separate Korean word spacer. However this pipeline approach has an obvious flaw of error propagation, since the POS tagger cannot correct word spacing errors. In this paper, we describe a joint model for Korean word spacing and POS tagging using structural SVM to avoid error propagation and improve word spacing by utilizing POS information. In the case of a pipeline approach, we could achieve a 96.77% morpheme-based F-measure for POS tagging. Using the joint model, we could achieve a 96.99% morpheme-based F-measure for POS tagging. Experimental results show that the joint model outperforms the pipeline approach. ․본 연구는 미래창조과학부 및 한국산업기술평가관리원의 산업융합원천기 술개발사업(정보통신) [10044577, 휴먼 지식증강 서비스를 위한 지능진 화형 WiseQA 플랫폼 기술 개발]과 [2013년도 강원대 전임교원 기본연구 비(하반기)] 사업의 일환으로 수행하였음 ․이 논문은 2013 한국컴퓨터종합학술대회에서 &#39;Structural SVM을 이용한 한국어 띄어쓰기 및 품사 태깅 결합 모델&#39;의 제목으로 발표된 논문을 확장 한 것임 † 종신회원 논문접수 심사완료 : : : 강원대학교 컴퓨터과학과 교수 l...</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="bb0bc7c25f5e780879346908becf0d03" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":88368653,"asset_id":82772018,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/88368653/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="82772018"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="82772018"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 82772018; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=82772018]").text(description); $(".js-view-count[data-work-id=82772018]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 82772018; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='82772018']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 82772018, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "bb0bc7c25f5e780879346908becf0d03" } } $('.js-work-strip[data-work-id=82772018]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":82772018,"title":"Structural SVM을 이용한 한국어 띄어쓰기 및 품사 태깅 결합 모델 (Joint Models for Korean Word Spacing and POS Tagging using Structural SVM)","translated_title":"","metadata":{"abstract":"Typically, a Korean Part-of-speech (POS) tagger takes the inputs that are produced by a separate Korean word spacer. However this pipeline approach has an obvious flaw of error propagation, since the POS tagger cannot correct word spacing errors. In this paper, we describe a joint model for Korean word spacing and POS tagging using structural SVM to avoid error propagation and improve word spacing by utilizing POS information. In the case of a pipeline approach, we could achieve a 96.77% morpheme-based F-measure for POS tagging. Using the joint model, we could achieve a 96.99% morpheme-based F-measure for POS tagging. Experimental results show that the joint model outperforms the pipeline approach. ․본 연구는 미래창조과학부 및 한국산업기술평가관리원의 산업융합원천기 술개발사업(정보통신) [10044577, 휴먼 지식증강 서비스를 위한 지능진 화형 WiseQA 플랫폼 기술 개발]과 [2013년도 강원대 전임교원 기본연구 비(하반기)] 사업의 일환으로 수행하였음 ․이 논문은 2013 한국컴퓨터종합학술대회에서 \u0026#39;Structural SVM을 이용한 한국어 띄어쓰기 및 품사 태깅 결합 모델\u0026#39;의 제목으로 발표된 논문을 확장 한 것임 † 종신회원 논문접수 심사완료 : : : 강원대학교 컴퓨터과학과 교수 l..."},"translated_abstract":"Typically, a Korean Part-of-speech (POS) tagger takes the inputs that are produced by a separate Korean word spacer. However this pipeline approach has an obvious flaw of error propagation, since the POS tagger cannot correct word spacing errors. In this paper, we describe a joint model for Korean word spacing and POS tagging using structural SVM to avoid error propagation and improve word spacing by utilizing POS information. In the case of a pipeline approach, we could achieve a 96.77% morpheme-based F-measure for POS tagging. Using the joint model, we could achieve a 96.99% morpheme-based F-measure for POS tagging. Experimental results show that the joint model outperforms the pipeline approach. ․본 연구는 미래창조과학부 및 한국산업기술평가관리원의 산업융합원천기 술개발사업(정보통신) [10044577, 휴먼 지식증강 서비스를 위한 지능진 화형 WiseQA 플랫폼 기술 개발]과 [2013년도 강원대 전임교원 기본연구 비(하반기)] 사업의 일환으로 수행하였음 ․이 논문은 2013 한국컴퓨터종합학술대회에서 \u0026#39;Structural SVM을 이용한 한국어 띄어쓰기 및 품사 태깅 결합 모델\u0026#39;의 제목으로 발표된 논문을 확장 한 것임 † 종신회원 논문접수 심사완료 : : : 강원대학교 컴퓨터과학과 교수 l...","internal_url":"https://www.academia.edu/82772018/Structural_SVM%EC%9D%84_%EC%9D%B4%EC%9A%A9%ED%95%9C_%ED%95%9C%EA%B5%AD%EC%96%B4_%EB%9D%84%EC%96%B4%EC%93%B0%EA%B8%B0_%EB%B0%8F_%ED%92%88%EC%82%AC_%ED%83%9C%EA%B9%85_%EA%B2%B0%ED%95%A9_%EB%AA%A8%EB%8D%B8_Joint_Models_for_Korean_Word_Spacing_and_POS_Tagging_using_Structural_SVM_","translated_internal_url":"","created_at":"2022-07-07T21:34:36.387-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":88368653,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368653/thumbnails/1.jpg","file_name":"09.pdf","download_url":"https://www.academia.edu/attachments/88368653/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Structural_SVM.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368653/09-libre.pdf?1657338801=\u0026response-content-disposition=attachment%3B+filename%3DStructural_SVM.pdf\u0026Expires=1733028036\u0026Signature=Pe7eogUmhYg-ZWY0DwLdDhOTv5At4Hw1LGZYnaZA~essu5x3It1zK5zS40POKolxxMwMUE7dwPN9tjttWJ6Y-~cNTi6JPTEZyXo05eOjsSCbACceiNUv6v4IEX37rPGIDMO2veEa6qilca-hk0X-se5kPSI1JH52nNywFcj5HXdM-tnExKbIXsY7coJKoMShPhI4J1-vKD7VEOjrWrS55bZ9UuFJ7uCEG2H2e0eWN9Cu-CgHaDG9jf29LLTDtMWEIGujLyRJe1Xqz9En4Z4JqIQMpSqDrwi7RyesjSNaaAT8Do5ET1RXqNix9l-0Ue2fB~z1Gv-Aogvz6CjgYNrcAA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Structural_SVM을_이용한_한국어_띄어쓰기_및_품사_태깅_결합_모델_Joint_Models_for_Korean_Word_Spacing_and_POS_Tagging_using_Structural_SVM_","translated_slug":"","page_count":7,"language":"ko","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":88368653,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368653/thumbnails/1.jpg","file_name":"09.pdf","download_url":"https://www.academia.edu/attachments/88368653/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Structural_SVM.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368653/09-libre.pdf?1657338801=\u0026response-content-disposition=attachment%3B+filename%3DStructural_SVM.pdf\u0026Expires=1733028036\u0026Signature=Pe7eogUmhYg-ZWY0DwLdDhOTv5At4Hw1LGZYnaZA~essu5x3It1zK5zS40POKolxxMwMUE7dwPN9tjttWJ6Y-~cNTi6JPTEZyXo05eOjsSCbACceiNUv6v4IEX37rPGIDMO2veEa6qilca-hk0X-se5kPSI1JH52nNywFcj5HXdM-tnExKbIXsY7coJKoMShPhI4J1-vKD7VEOjrWrS55bZ9UuFJ7uCEG2H2e0eWN9Cu-CgHaDG9jf29LLTDtMWEIGujLyRJe1Xqz9En4Z4JqIQMpSqDrwi7RyesjSNaaAT8Do5ET1RXqNix9l-0Ue2fB~z1Gv-Aogvz6CjgYNrcAA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[],"urls":[{"id":21998392,"url":"https://web.archive.org/web/20180424232914/http://kiise.or.kr/e_journal/2013/12/sa/pdf/09.pdf"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="82772001"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/82772001/English_to_Korean_Machine_Translation_using_Image_Information"><img alt="Research paper thumbnail of English-to-Korean Machine Translation using Image Information" class="work-thumbnail" src="https://attachments.academia-assets.com/88368182/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/82772001/English_to_Korean_Machine_Translation_using_Image_Information">English-to-Korean Machine Translation using Image Information</a></div><div class="wp-workCard_item"><span>Journal of KIISE</span><span>, 2019</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="72e95c65df0c1f13357443a6a848ec4c" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":88368182,"asset_id":82772001,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/88368182/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="82772001"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="82772001"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 82772001; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=82772001]").text(description); $(".js-view-count[data-work-id=82772001]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 82772001; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='82772001']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 82772001, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "72e95c65df0c1f13357443a6a848ec4c" } } $('.js-work-strip[data-work-id=82772001]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":82772001,"title":"English-to-Korean Machine Translation using Image Information","translated_title":"","metadata":{"publisher":"Korean Institute of Information Scientists and Engineers","publication_date":{"day":null,"month":null,"year":2019,"errors":{}},"publication_name":"Journal of KIISE"},"translated_abstract":null,"internal_url":"https://www.academia.edu/82772001/English_to_Korean_Machine_Translation_using_Image_Information","translated_internal_url":"","created_at":"2022-07-07T21:34:05.277-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":88368182,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368182/thumbnails/1.jpg","file_name":"12.pdf","download_url":"https://www.academia.edu/attachments/88368182/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"English_to_Korean_Machine_Translation_us.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368182/12-libre.pdf?1657338107=\u0026response-content-disposition=attachment%3B+filename%3DEnglish_to_Korean_Machine_Translation_us.pdf\u0026Expires=1733028036\u0026Signature=UORXcJfbuTEGrxq5naiCmfknuNoEExZOjcGZRhPO~siIC6sS2I3wS290XcYWkE1Z59aszjPk0opux6BfhQgIeP~FYvtWCIAhPhrJUlCUwu2vktaajKU~jWyg7tCJwlQ4XoVVHaYIdUqFqty9KrUuTTTJGl71To6e3W7jeZGm9OjMbqiFHr0XTa1IP7mr87dwLTldn5LIYwqd9cNXccrK6x4kLzTsxwoJwxvdI1R-gAIJzZtE62pDeiZnKl-4kYErjbefLOZAQIbxuhz8DWDJ4VNbKIFrJCTUN8lo6c4-cLRbiRzv7JN5vWkTCUvsYE8ewNXEZNWqQE7F5SDpA3U4AQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"English_to_Korean_Machine_Translation_using_Image_Information","translated_slug":"","page_count":7,"language":"ko","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":88368182,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368182/thumbnails/1.jpg","file_name":"12.pdf","download_url":"https://www.academia.edu/attachments/88368182/download_file?st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"English_to_Korean_Machine_Translation_us.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368182/12-libre.pdf?1657338107=\u0026response-content-disposition=attachment%3B+filename%3DEnglish_to_Korean_Machine_Translation_us.pdf\u0026Expires=1733028036\u0026Signature=UORXcJfbuTEGrxq5naiCmfknuNoEExZOjcGZRhPO~siIC6sS2I3wS290XcYWkE1Z59aszjPk0opux6BfhQgIeP~FYvtWCIAhPhrJUlCUwu2vktaajKU~jWyg7tCJwlQ4XoVVHaYIdUqFqty9KrUuTTTJGl71To6e3W7jeZGm9OjMbqiFHr0XTa1IP7mr87dwLTldn5LIYwqd9cNXccrK6x4kLzTsxwoJwxvdI1R-gAIJzZtE62pDeiZnKl-4kYErjbefLOZAQIbxuhz8DWDJ4VNbKIFrJCTUN8lo6c4-cLRbiRzv7JN5vWkTCUvsYE8ewNXEZNWqQE7F5SDpA3U4AQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="82771977"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/82771977/End_to_end_Korean_Document_Summarization_using_Copy_Mechanism_and_Input_feeding"><img alt="Research paper thumbnail of End-to-end Korean Document Summarization using Copy Mechanism and Input-feeding" class="work-thumbnail" src="https://attachments.academia-assets.com/88368176/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/82771977/End_to_end_Korean_Document_Summarization_using_Copy_Mechanism_and_Input_feeding">End-to-end Korean Document Summarization using Copy Mechanism and Input-feeding</a></div><div class="wp-workCard_item"><span>Journal of KIISE</span><span>, 2017</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="21b1dd1cf71c2f9a17e85b62ff8c6993" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":88368176,"asset_id":82771977,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/88368176/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="82771977"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="82771977"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 82771977; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=82771977]").text(description); $(".js-view-count[data-work-id=82771977]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 82771977; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='82771977']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 82771977, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "21b1dd1cf71c2f9a17e85b62ff8c6993" } } $('.js-work-strip[data-work-id=82771977]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":82771977,"title":"End-to-end Korean Document Summarization using Copy Mechanism and Input-feeding","translated_title":"","metadata":{"publisher":"Korean Institute of Information Scientists and Engineers","grobid_abstract":"In this paper, the copy mechanism and input feeding are applied to recurrent neural network(RNN)-search model in a Korean-document summarization in an end-to-end manner. In addition, the performances of the document summarizations are compared according to the model and the tokenization format; accordingly, the syllable-unit, morpheme-unit, and hybrid-unit tokenization formats are compared. For the experiments, Internet newspaper articles were collected to construct a Korean-document summary data set (train set: 30291 documents; development set: 3786 documents; test set: 3705 documents). When the format was tokenized as the morpheme-unit, the models with the input feeding and the copy mechanism showed the highest performances of ROUGE-1 35.92, ROUGE-2 15.37, and ROUGE-L 29.45.","publication_date":{"day":null,"month":null,"year":2017,"errors":{}},"publication_name":"Journal of KIISE","grobid_abstract_attachment_id":88368176},"translated_abstract":null,"internal_url":"https://www.academia.edu/82771977/End_to_end_Korean_Document_Summarization_using_Copy_Mechanism_and_Input_feeding","translated_internal_url":"","created_at":"2022-07-07T21:33:31.619-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":88368176,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368176/thumbnails/1.jpg","file_name":"08.pdf","download_url":"https://www.academia.edu/attachments/88368176/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"End_to_end_Korean_Document_Summarization.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368176/08-libre.pdf?1657338112=\u0026response-content-disposition=attachment%3B+filename%3DEnd_to_end_Korean_Document_Summarization.pdf\u0026Expires=1733028036\u0026Signature=bwnByb0ZBLg0QQ6v9mcbk3jt74qBwPvxS3ek4wTrvcweNeJ3zVX4FMs5VWdquf8QSy~Yt~LHf-PslCBtM4jGkg5LxMQlM~evZIXnJiXUaCCED2HMqZo2UANFN2z1k24QdWmLNGYNVfn19IUvvejyuy7Aa3TMv2qKuJOmgIJ0OoEimTIGUXqrQglYzKbH-MnIAMHS1Sg0nQzbLdaA9Hvxom3YLcDgS0bR5PIFAqR9X~txkbd0xb9h2bhSfE-XqD1uf8XJmKSroFiEqotffq5h-FaLXvuoG3YKWFjf6lVrJJxiGaXxU6cUGb8fa44KPTXmKqMqGL-lfC0rzHTcPOs-cw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"End_to_end_Korean_Document_Summarization_using_Copy_Mechanism_and_Input_feeding","translated_slug":"","page_count":7,"language":"ko","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":88368176,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368176/thumbnails/1.jpg","file_name":"08.pdf","download_url":"https://www.academia.edu/attachments/88368176/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"End_to_end_Korean_Document_Summarization.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368176/08-libre.pdf?1657338112=\u0026response-content-disposition=attachment%3B+filename%3DEnd_to_end_Korean_Document_Summarization.pdf\u0026Expires=1733028036\u0026Signature=bwnByb0ZBLg0QQ6v9mcbk3jt74qBwPvxS3ek4wTrvcweNeJ3zVX4FMs5VWdquf8QSy~Yt~LHf-PslCBtM4jGkg5LxMQlM~evZIXnJiXUaCCED2HMqZo2UANFN2z1k24QdWmLNGYNVfn19IUvvejyuy7Aa3TMv2qKuJOmgIJ0OoEimTIGUXqrQglYzKbH-MnIAMHS1Sg0nQzbLdaA9Hvxom3YLcDgS0bR5PIFAqR9X~txkbd0xb9h2bhSfE-XqD1uf8XJmKSroFiEqotffq5h-FaLXvuoG3YKWFjf6lVrJJxiGaXxU6cUGb8fa44KPTXmKqMqGL-lfC0rzHTcPOs-cw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="82771953"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/82771953/SiteQ_Engineering_high_performance_QA_system_using_lexico_semantic_pattern_matching_and_shallow_NLP"><img alt="Research paper thumbnail of SiteQ: Engineering high performance QA system using lexico-semantic pattern matching and shallow NLP" class="work-thumbnail" src="https://attachments.academia-assets.com/88368787/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/82771953/SiteQ_Engineering_high_performance_QA_system_using_lexico_semantic_pattern_matching_and_shallow_NLP">SiteQ: Engineering high performance QA system using lexico-semantic pattern matching and shallow NLP</a></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="9f75a17ec2c17496cdc14b7059d219b9" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":88368787,"asset_id":82771953,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/88368787/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="82771953"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="82771953"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 82771953; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=82771953]").text(description); $(".js-view-count[data-work-id=82771953]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 82771953; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='82771953']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 82771953, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "9f75a17ec2c17496cdc14b7059d219b9" } } $('.js-work-strip[data-work-id=82771953]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":82771953,"title":"SiteQ: Engineering high performance QA system using lexico-semantic pattern matching and shallow NLP","translated_title":"","metadata":{"grobid_abstract":"In TREC-10, we participated in the web track (only ad-hoc task) and the QA track (only main task). In the QA track, our QA system (SiteQ) has general architecture with three processing steps: question processing, passage selection and answer processing. The key technique is LSP's (Lexico-Semantic Patterns) that are composed of linguistic entries and semantic types. LSP grammars constructed from various resources are used for answer type determination and answer matching. We also adapt AAD (Abbreviation-Appositive-Definition) processing for the queries that answer type cannot be determined or expected, encyclopedia search for increasing the matching coverage between query terms and passages, and pivot detection for the distance calculation with answer candidates. We used two-level answer types consisted of 18 upper-level types and 47 lower-level types. Semantic category dictionary, WordNet, POS combined with lexicography and a stemmer were all applied to construct the LSP knowledge base. CSMT (Category Sense-code Mapping Table) tried to find answer types using the matching between semantic categories and sense-codes from WordNet. Evaluation shows that MRR for 492 questions is 0.320 (strict), which is considerably higher than the average MRR of other 67 runs. In the Web track, we focused on the effectiveness of both noun phrase extraction and our new PRF (Pseudo Relevance Feedback). We confirmed that our query expansion using PRF with TSV function adapting TF factor contributed to better performance, but noun phrases did not contribute much. It needs more observations for us to make elaborate rules of tag patterns for the construction of better noun phrases.","publication_date":{"day":null,"month":null,"year":2001,"errors":{}},"grobid_abstract_attachment_id":88368787},"translated_abstract":null,"internal_url":"https://www.academia.edu/82771953/SiteQ_Engineering_high_performance_QA_system_using_lexico_semantic_pattern_matching_and_shallow_NLP","translated_internal_url":"","created_at":"2022-07-07T21:32:55.566-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":88368787,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368787/thumbnails/1.jpg","file_name":"siteq_trec10.pdf","download_url":"https://www.academia.edu/attachments/88368787/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"SiteQ_Engineering_high_performance_QA_sy.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368787/siteq_trec10-libre.pdf?1657338761=\u0026response-content-disposition=attachment%3B+filename%3DSiteQ_Engineering_high_performance_QA_sy.pdf\u0026Expires=1733028037\u0026Signature=ZLIrmFoTV1~-sI5up7K55i0o2j1XJtYcx3FQsm4Hnu2ow7JkV5xwlScu4WDlOWer9z-qFxJK9szYUQTVYG-P8rJ-dFJTlzpXiVZbrV13pR4vXqX2BAuop9iRrW2XchK2TkYZ0UclH8ESn11OcVHSvJpshSLIRNDkPxrSy5r-NuWMjV-P3rbZKI76DK7hPQzFr9IGFy~S-rhiYJ9tRC1kqtJTj0I12TJ-NSTmfZHGTHliw4s9QF8tFClwUnLoE9tEKiz4yJXRh4x5gCjdrKhbP2CL1z2uRV294jgRJmoVKloP3vK-k6Tr7TlffSRBU-Zsugbmvn--EJ0MifnBlDsvZw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"SiteQ_Engineering_high_performance_QA_system_using_lexico_semantic_pattern_matching_and_shallow_NLP","translated_slug":"","page_count":10,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":88368787,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368787/thumbnails/1.jpg","file_name":"siteq_trec10.pdf","download_url":"https://www.academia.edu/attachments/88368787/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"SiteQ_Engineering_high_performance_QA_sy.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368787/siteq_trec10-libre.pdf?1657338761=\u0026response-content-disposition=attachment%3B+filename%3DSiteQ_Engineering_high_performance_QA_sy.pdf\u0026Expires=1733028037\u0026Signature=ZLIrmFoTV1~-sI5up7K55i0o2j1XJtYcx3FQsm4Hnu2ow7JkV5xwlScu4WDlOWer9z-qFxJK9szYUQTVYG-P8rJ-dFJTlzpXiVZbrV13pR4vXqX2BAuop9iRrW2XchK2TkYZ0UclH8ESn11OcVHSvJpshSLIRNDkPxrSy5r-NuWMjV-P3rbZKI76DK7hPQzFr9IGFy~S-rhiYJ9tRC1kqtJTj0I12TJ-NSTmfZHGTHliw4s9QF8tFClwUnLoE9tEKiz4yJXRh4x5gCjdrKhbP2CL1z2uRV294jgRJmoVKloP3vK-k6Tr7TlffSRBU-Zsugbmvn--EJ0MifnBlDsvZw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":143286,"name":"Noun Phrase","url":"https://www.academia.edu/Documents/in/Noun_Phrase"},{"id":155958,"name":"Pattern Matching","url":"https://www.academia.edu/Documents/in/Pattern_Matching"},{"id":212580,"name":"Query Expansion","url":"https://www.academia.edu/Documents/in/Query_Expansion"},{"id":246163,"name":"Knowledge base","url":"https://www.academia.edu/Documents/in/Knowledge_base"},{"id":274507,"name":"TREC","url":"https://www.academia.edu/Documents/in/TREC"},{"id":297691,"name":"High performance","url":"https://www.academia.edu/Documents/in/High_performance"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="82771763"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/82771763/Korean_Semantic_Role_Labeling_with_Bidirectional_Encoder_Representations_from_Transformers_and_Simple_Semantic_Information"><img alt="Research paper thumbnail of Korean Semantic Role Labeling with Bidirectional Encoder Representations from Transformers and Simple Semantic Information" class="work-thumbnail" src="https://attachments.academia-assets.com/88368087/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/82771763/Korean_Semantic_Role_Labeling_with_Bidirectional_Encoder_Representations_from_Transformers_and_Simple_Semantic_Information">Korean Semantic Role Labeling with Bidirectional Encoder Representations from Transformers and Simple Semantic Information</a></div><div class="wp-workCard_item"><span>Applied Sciences</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">State-of-the-art semantic role labeling (SRL) performance has been achieved using neural network ...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">State-of-the-art semantic role labeling (SRL) performance has been achieved using neural network models by incorporating syntactic feature information such as dependency trees. In recent years, breakthroughs achieved using end-to-end neural network models have resulted in a state-of-the-art SRL performance even without syntactic features. With the advent of a language model called bidirectional encoder representations from transformers (BERT), another breakthrough was witnessed. Even though the semantic information of each word constituting a sentence is important in determining the meaning of a word, previous studies regarding the end-to-end neural network method did not utilize semantic information. In this study, we propose a BERT-based SRL model that uses simple semantic information without syntactic feature information. To obtain the latter, we used PropBank, which described the relational information between predicates and arguments. In addition, text-originated feature inform...</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="454597bb8348c8b50e16bae5f6eddabf" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":88368087,"asset_id":82771763,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/88368087/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="82771763"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="82771763"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 82771763; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=82771763]").text(description); $(".js-view-count[data-work-id=82771763]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 82771763; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='82771763']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 82771763, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "454597bb8348c8b50e16bae5f6eddabf" } } $('.js-work-strip[data-work-id=82771763]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":82771763,"title":"Korean Semantic Role Labeling with Bidirectional Encoder Representations from Transformers and Simple Semantic Information","translated_title":"","metadata":{"abstract":"State-of-the-art semantic role labeling (SRL) performance has been achieved using neural network models by incorporating syntactic feature information such as dependency trees. In recent years, breakthroughs achieved using end-to-end neural network models have resulted in a state-of-the-art SRL performance even without syntactic features. With the advent of a language model called bidirectional encoder representations from transformers (BERT), another breakthrough was witnessed. Even though the semantic information of each word constituting a sentence is important in determining the meaning of a word, previous studies regarding the end-to-end neural network method did not utilize semantic information. In this study, we propose a BERT-based SRL model that uses simple semantic information without syntactic feature information. To obtain the latter, we used PropBank, which described the relational information between predicates and arguments. In addition, text-originated feature inform...","publisher":"MDPI AG","publication_name":"Applied Sciences"},"translated_abstract":"State-of-the-art semantic role labeling (SRL) performance has been achieved using neural network models by incorporating syntactic feature information such as dependency trees. In recent years, breakthroughs achieved using end-to-end neural network models have resulted in a state-of-the-art SRL performance even without syntactic features. With the advent of a language model called bidirectional encoder representations from transformers (BERT), another breakthrough was witnessed. Even though the semantic information of each word constituting a sentence is important in determining the meaning of a word, previous studies regarding the end-to-end neural network method did not utilize semantic information. In this study, we propose a BERT-based SRL model that uses simple semantic information without syntactic feature information. To obtain the latter, we used PropBank, which described the relational information between predicates and arguments. In addition, text-originated feature inform...","internal_url":"https://www.academia.edu/82771763/Korean_Semantic_Role_Labeling_with_Bidirectional_Encoder_Representations_from_Transformers_and_Simple_Semantic_Information","translated_internal_url":"","created_at":"2022-07-07T21:30:32.988-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":88368087,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368087/thumbnails/1.jpg","file_name":"pdf.pdf","download_url":"https://www.academia.edu/attachments/88368087/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Korean_Semantic_Role_Labeling_with_Bidir.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368087/pdf-libre.pdf?1657337829=\u0026response-content-disposition=attachment%3B+filename%3DKorean_Semantic_Role_Labeling_with_Bidir.pdf\u0026Expires=1733028037\u0026Signature=M7JZuIgWlyENOnR-wwIKwPvqZSkiHGdQQ5sHSdypPszorJY8qbShT6Wex4tEgTC~KNFDwTQlr4E5HDHtIvcUNw~lMHcMGwKNQhviAUI4QJ~f3G1y4k3fLfHXxwH2L7kJeEWRqrQMMWwXY21fwLBf~7tR6TGgsc7kILHwx5ipTrADUIOWeJ9iVv2RG0fECzlLsDjZc9Sz0csZHFdd8H~9PKFH9OpC9KD~6NG24nJKHgGv~0DSKN4OMh~Lctu1mP1itJ8LbiDb~dF~PyJ5vFXR-~hs20OEqSIC3dZ0IaBzJ9kOa7KiYLWZ28crM0lzCZNDwy6jEHStat3KYc6ZA8ZZaQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Korean_Semantic_Role_Labeling_with_Bidirectional_Encoder_Representations_from_Transformers_and_Simple_Semantic_Information","translated_slug":"","page_count":9,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":88368087,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368087/thumbnails/1.jpg","file_name":"pdf.pdf","download_url":"https://www.academia.edu/attachments/88368087/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Korean_Semantic_Role_Labeling_with_Bidir.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368087/pdf-libre.pdf?1657337829=\u0026response-content-disposition=attachment%3B+filename%3DKorean_Semantic_Role_Labeling_with_Bidir.pdf\u0026Expires=1733028037\u0026Signature=M7JZuIgWlyENOnR-wwIKwPvqZSkiHGdQQ5sHSdypPszorJY8qbShT6Wex4tEgTC~KNFDwTQlr4E5HDHtIvcUNw~lMHcMGwKNQhviAUI4QJ~f3G1y4k3fLfHXxwH2L7kJeEWRqrQMMWwXY21fwLBf~7tR6TGgsc7kILHwx5ipTrADUIOWeJ9iVv2RG0fECzlLsDjZc9Sz0csZHFdd8H~9PKFH9OpC9KD~6NG24nJKHgGv~0DSKN4OMh~Lctu1mP1itJ8LbiDb~dF~PyJ5vFXR-~hs20OEqSIC3dZ0IaBzJ9kOa7KiYLWZ28crM0lzCZNDwy6jEHStat3KYc6ZA8ZZaQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":159232,"name":"Applied Sciences","url":"https://www.academia.edu/Documents/in/Applied_Sciences"}],"urls":[{"id":21998260,"url":"https://www.mdpi.com/2076-3417/12/12/5995/pdf"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="72121117"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/72121117/Systematic_Construction_of_Hierarchical_Classifier_in_SVM_Based_Text_Categorization"><img alt="Research paper thumbnail of Systematic Construction of Hierarchical Classifier in SVM-Based Text Categorization" class="work-thumbnail" src="https://attachments.academia-assets.com/81178132/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/72121117/Systematic_Construction_of_Hierarchical_Classifier_in_SVM_Based_Text_Categorization">Systematic Construction of Hierarchical Classifier in SVM-Based Text Categorization</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Abstract. In a text categorization task, classification on some hierar-chy of classes shows bette...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">Abstract. In a text categorization task, classification on some hierar-chy of classes shows better results than the case without the hierarchy. In current environments where large amount of documents are divided into several subgroups with a hierarchy between them, it is more natural and appropriate to use a hierarchical classification method. We intro-duce a new internal node evaluation scheme which is very helpful to the development process of a hierarchical classifier. We also show that the hierarchical classifier construction method using this measure yields a classifier with better classification performance especially when applied to the classification task with large depth of hierarchy. 1</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="1ca7741dbc512e9865436db12e0f08df" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":81178132,"asset_id":72121117,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/81178132/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="72121117"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="72121117"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 72121117; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=72121117]").text(description); $(".js-view-count[data-work-id=72121117]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 72121117; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='72121117']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 72121117, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "1ca7741dbc512e9865436db12e0f08df" } } $('.js-work-strip[data-work-id=72121117]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":72121117,"title":"Systematic Construction of Hierarchical Classifier in SVM-Based Text Categorization","translated_title":"","metadata":{"abstract":"Abstract. In a text categorization task, classification on some hierar-chy of classes shows better results than the case without the hierarchy. In current environments where large amount of documents are divided into several subgroups with a hierarchy between them, it is more natural and appropriate to use a hierarchical classification method. We intro-duce a new internal node evaluation scheme which is very helpful to the development process of a hierarchical classifier. We also show that the hierarchical classifier construction method using this measure yields a classifier with better classification performance especially when applied to the classification task with large depth of hierarchy. 1","publication_date":{"day":null,"month":null,"year":2004,"errors":{}}},"translated_abstract":"Abstract. In a text categorization task, classification on some hierar-chy of classes shows better results than the case without the hierarchy. In current environments where large amount of documents are divided into several subgroups with a hierarchy between them, it is more natural and appropriate to use a hierarchical classification method. We intro-duce a new internal node evaluation scheme which is very helpful to the development process of a hierarchical classifier. We also show that the hierarchical classifier construction method using this measure yields a classifier with better classification performance especially when applied to the classification task with large depth of hierarchy. 1","internal_url":"https://www.academia.edu/72121117/Systematic_Construction_of_Hierarchical_Classifier_in_SVM_Based_Text_Categorization","translated_internal_url":"","created_at":"2022-02-21T10:32:13.980-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":81178132,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/81178132/thumbnails/1.jpg","file_name":"hierc_ijcnlp.pdf","download_url":"https://www.academia.edu/attachments/81178132/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Systematic_Construction_of_Hierarchical.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/81178132/hierc_ijcnlp-libre.pdf?1645469013=\u0026response-content-disposition=attachment%3B+filename%3DSystematic_Construction_of_Hierarchical.pdf\u0026Expires=1733028037\u0026Signature=ZWxc9Z9SI~PsKkO~kegBJU9jItffjeQkGfRJR1skG3C84Gz-s~ihOCs8ytGujePUB7i7enFTb2ZLchCybM~K~EyWq7BWgGMhHKRc5h3MDCt5J5ddTa5FhsviiGmM4GgZVnJoz5e~uMWBvCVLtDTXWPmvoqBFYjX-X-Ufbkr5vSPCEejW2LGI3QCA3dI-QwHWlv5hVmUekIU4~bIvkcnqbpcVo2K83yKpiIlSXnDIoCzeZ9z9jPnPlexqcn2apj6r0NWzX1CkSmMJpkDGe2Hv-TBFB4k3wNxZavQPpSzjeAvuDyxUrN7g18Pb5RpjHq~MCwU4dBehaWO8an9Z5EhyRA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Systematic_Construction_of_Hierarchical_Classifier_in_SVM_Based_Text_Categorization","translated_slug":"","page_count":8,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":81178132,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/81178132/thumbnails/1.jpg","file_name":"hierc_ijcnlp.pdf","download_url":"https://www.academia.edu/attachments/81178132/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Systematic_Construction_of_Hierarchical.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/81178132/hierc_ijcnlp-libre.pdf?1645469013=\u0026response-content-disposition=attachment%3B+filename%3DSystematic_Construction_of_Hierarchical.pdf\u0026Expires=1733028037\u0026Signature=ZWxc9Z9SI~PsKkO~kegBJU9jItffjeQkGfRJR1skG3C84Gz-s~ihOCs8ytGujePUB7i7enFTb2ZLchCybM~K~EyWq7BWgGMhHKRc5h3MDCt5J5ddTa5FhsviiGmM4GgZVnJoz5e~uMWBvCVLtDTXWPmvoqBFYjX-X-Ufbkr5vSPCEejW2LGI3QCA3dI-QwHWlv5hVmUekIU4~bIvkcnqbpcVo2K83yKpiIlSXnDIoCzeZ9z9jPnPlexqcn2apj6r0NWzX1CkSmMJpkDGe2Hv-TBFB4k3wNxZavQPpSzjeAvuDyxUrN7g18Pb5RpjHq~MCwU4dBehaWO8an9Z5EhyRA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":582043,"name":"Development Process","url":"https://www.academia.edu/Documents/in/Development_Process"}],"urls":[{"id":17904128,"url":"http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.535.6381\u0026rep=rep1\u0026type=pdf"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="72121116"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/72121116/Automatic_WordNet_mapping_using_word_sense_disambiguation"><img alt="Research paper thumbnail of Automatic WordNet mapping using word sense disambiguation" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/72121116/Automatic_WordNet_mapping_using_word_sense_disambiguation">Automatic WordNet mapping using word sense disambiguation</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">This paper presents the automatic construction of a Korean WordNet from pre-existing lexical reso...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">This paper presents the automatic construction of a Korean WordNet from pre-existing lexical resources. A set of automatic WSD techniques is described for linking Korean words collected from a bilingual MRD to English WordNet synsets.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="72121116"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="72121116"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 72121116; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=72121116]").text(description); $(".js-view-count[data-work-id=72121116]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 72121116; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='72121116']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 72121116, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=72121116]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":72121116,"title":"Automatic WordNet mapping using word sense disambiguation","translated_title":"","metadata":{"abstract":"This paper presents the automatic construction of a Korean WordNet from pre-existing lexical resources. A set of automatic WSD techniques is described for linking Korean words collected from a bilingual MRD to English WordNet synsets.","publication_date":{"day":null,"month":null,"year":2000,"errors":{}}},"translated_abstract":"This paper presents the automatic construction of a Korean WordNet from pre-existing lexical resources. A set of automatic WSD techniques is described for linking Korean words collected from a bilingual MRD to English WordNet synsets.","internal_url":"https://www.academia.edu/72121116/Automatic_WordNet_mapping_using_word_sense_disambiguation","translated_internal_url":"","created_at":"2022-02-21T10:32:13.826-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Automatic_WordNet_mapping_using_word_sense_disambiguation","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[],"urls":[{"id":17904127,"url":"http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.12.8959\u0026rep=rep1\u0026type=pdf"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> </div><div class="profile--tab_content_container js-tab-pane tab-pane" data-section-id="13618814" id="papers"><div class="js-work-strip profile--work_container" data-work-id="96477146"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/96477146/Transformer_Decoding_Speed_Improvement_using_CAN_and_Dense_Synthesizer"><img alt="Research paper thumbnail of Transformer Decoding Speed Improvement using CAN and Dense Synthesizer" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/96477146/Transformer_Decoding_Speed_Improvement_using_CAN_and_Dense_Synthesizer">Transformer Decoding Speed Improvement using CAN and Dense Synthesizer</a></div><div class="wp-workCard_item"><span>KIISE Transactions on Computing Practices</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="96477146"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="96477146"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 96477146; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=96477146]").text(description); $(".js-view-count[data-work-id=96477146]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 96477146; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='96477146']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 96477146, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=96477146]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":96477146,"title":"Transformer Decoding Speed Improvement using CAN and Dense Synthesizer","translated_title":"","metadata":{"publisher":"Korean Institute of Information Scientists and Engineers","publication_name":"KIISE Transactions on Computing Practices"},"translated_abstract":null,"internal_url":"https://www.academia.edu/96477146/Transformer_Decoding_Speed_Improvement_using_CAN_and_Dense_Synthesizer","translated_internal_url":"","created_at":"2023-02-07T07:13:52.530-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Transformer_Decoding_Speed_Improvement_using_CAN_and_Dense_Synthesizer","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":117893,"name":"Transformer","url":"https://www.academia.edu/Documents/in/Transformer"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="96477145"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/96477145/Coreference_Resolution_with_Hierarchical_Pointer_Networks_Based_on_Pointing_Methods"><img alt="Research paper thumbnail of Coreference Resolution with Hierarchical Pointer Networks Based on Pointing Methods" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/96477145/Coreference_Resolution_with_Hierarchical_Pointer_Networks_Based_on_Pointing_Methods">Coreference Resolution with Hierarchical Pointer Networks Based on Pointing Methods</a></div><div class="wp-workCard_item"><span>2020 IEEE International Conference on Big Data and Smart Computing (BigComp)</span><span>, 2020</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Coreference resolution is a type of discourse analysis task of natural language processing. The t...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">Coreference resolution is a type of discourse analysis task of natural language processing. The task entails a method of linking different words expressed in an arbitrary entity within a document. Pointer networks (Ptr-net) based on RNN encoder-decoder is capable of modeling the problem of a target class variable and learning and predicting a position corresponding to a given input sequence. A hierarchical RNN encoder-decoder is an extended model of the RNN encoder-decoder that performs encoding on a word-by-word basis for a given input sequence. It performs encoding on a sentence basis to predict the output result. Ptr-net suffers from performance degradation when the input is composed of multiple sentences, or when the length of the input sentence is long. To solve this problem, we propose a coreference resolution with a hierarchical pointer networks (HRPT) model based on pointing methods for all cases mentioned. The HRPT encodes word and sentence levels for the input sequence, consisting of multiple sentences. It uses both word and sentence-level information in the decoder. The pointing method for coreference resolution is a way of pointing to the position of the referenced word or the referenced pivot of the entity. Experimental results show that the proposed model is CoNLL F1 71.56%, which is 20.96% better than the rule-based model.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="96477145"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="96477145"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 96477145; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=96477145]").text(description); $(".js-view-count[data-work-id=96477145]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 96477145; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='96477145']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 96477145, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=96477145]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":96477145,"title":"Coreference Resolution with Hierarchical Pointer Networks Based on Pointing Methods","translated_title":"","metadata":{"abstract":"Coreference resolution is a type of discourse analysis task of natural language processing. The task entails a method of linking different words expressed in an arbitrary entity within a document. Pointer networks (Ptr-net) based on RNN encoder-decoder is capable of modeling the problem of a target class variable and learning and predicting a position corresponding to a given input sequence. A hierarchical RNN encoder-decoder is an extended model of the RNN encoder-decoder that performs encoding on a word-by-word basis for a given input sequence. It performs encoding on a sentence basis to predict the output result. Ptr-net suffers from performance degradation when the input is composed of multiple sentences, or when the length of the input sentence is long. To solve this problem, we propose a coreference resolution with a hierarchical pointer networks (HRPT) model based on pointing methods for all cases mentioned. The HRPT encodes word and sentence levels for the input sequence, consisting of multiple sentences. It uses both word and sentence-level information in the decoder. The pointing method for coreference resolution is a way of pointing to the position of the referenced word or the referenced pivot of the entity. Experimental results show that the proposed model is CoNLL F1 71.56%, which is 20.96% better than the rule-based model.","publisher":"IEEE","publication_date":{"day":null,"month":null,"year":2020,"errors":{}},"publication_name":"2020 IEEE International Conference on Big Data and Smart Computing (BigComp)"},"translated_abstract":"Coreference resolution is a type of discourse analysis task of natural language processing. The task entails a method of linking different words expressed in an arbitrary entity within a document. Pointer networks (Ptr-net) based on RNN encoder-decoder is capable of modeling the problem of a target class variable and learning and predicting a position corresponding to a given input sequence. A hierarchical RNN encoder-decoder is an extended model of the RNN encoder-decoder that performs encoding on a word-by-word basis for a given input sequence. It performs encoding on a sentence basis to predict the output result. Ptr-net suffers from performance degradation when the input is composed of multiple sentences, or when the length of the input sentence is long. To solve this problem, we propose a coreference resolution with a hierarchical pointer networks (HRPT) model based on pointing methods for all cases mentioned. The HRPT encodes word and sentence levels for the input sequence, consisting of multiple sentences. It uses both word and sentence-level information in the decoder. The pointing method for coreference resolution is a way of pointing to the position of the referenced word or the referenced pivot of the entity. Experimental results show that the proposed model is CoNLL F1 71.56%, which is 20.96% better than the rule-based model.","internal_url":"https://www.academia.edu/96477145/Coreference_Resolution_with_Hierarchical_Pointer_Networks_Based_on_Pointing_Methods","translated_internal_url":"","created_at":"2023-02-07T07:13:52.352-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Coreference_Resolution_with_Hierarchical_Pointer_Networks_Based_on_Pointing_Methods","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":60944,"name":"Coreference","url":"https://www.academia.edu/Documents/in/Coreference"},{"id":140897,"name":"Encoder","url":"https://www.academia.edu/Documents/in/Encoder"},{"id":961850,"name":"Sentence","url":"https://www.academia.edu/Documents/in/Sentence"}],"urls":[{"id":28771720,"url":"http://xplorestaging.ieee.org/ielx7/9050588/9070238/09070417.pdf?arnumber=9070417"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="96477144"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/96477144/S_2_Net_Machine_reading_comprehension_with_SRU_based_self_matching_networks"><img alt="Research paper thumbnail of S 2 ‐Net: Machine reading comprehension with SRU‐based self‐matching networks" class="work-thumbnail" src="https://attachments.academia-assets.com/98365356/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/96477144/S_2_Net_Machine_reading_comprehension_with_SRU_based_self_matching_networks">S 2 ‐Net: Machine reading comprehension with SRU‐based self‐matching networks</a></div><div class="wp-workCard_item"><span>ETRI Journal</span><span>, 2019</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="b114eeeb083aae23c8154e055df26e1a" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":98365356,"asset_id":96477144,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/98365356/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="96477144"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="96477144"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 96477144; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=96477144]").text(description); $(".js-view-count[data-work-id=96477144]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 96477144; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='96477144']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 96477144, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "b114eeeb083aae23c8154e055df26e1a" } } $('.js-work-strip[data-work-id=96477144]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":96477144,"title":"S 2 ‐Net: Machine reading comprehension with SRU‐based self‐matching networks","translated_title":"","metadata":{"publisher":"Wiley","grobid_abstract":"Machine reading comprehension refers to a machine's ability to understand a given context and determine the correct answer to a question in the context of question-answering applications. For example, machine reading comprehension should be able to understand the context \"2004년 건조기 시 장에… 의류 건조기 중 LG전자는 점유율 77.4%로 1위를 차지했다. (Machine dryer market in 2004 … LG Electronics ranked first with 77.4% of clothes dryers.)\" and determine the correct answer output \"LG 전자 (LG Electronics)\" in the context of a question like \"국내 건조기 시장 점유율 1 위 누구야? (Who is number 1 in the Korean dryer market share?)\". Machine reading comprehension has been performed on datasets, such as SQuAD of Stanford, bAbi of Facebook, and MS-MARCO of Microsoft [1-3]. Deep-learning models, such as DrQA, fastQA, R-Net, AoA reader, bidirectional flow (BiDAF), and Match-LSTM [4-9], are currently the focus of research. These deep-learning models perform encoding","publication_date":{"day":null,"month":null,"year":2019,"errors":{}},"publication_name":"ETRI Journal","grobid_abstract_attachment_id":98365356},"translated_abstract":null,"internal_url":"https://www.academia.edu/96477144/S_2_Net_Machine_reading_comprehension_with_SRU_based_self_matching_networks","translated_internal_url":"","created_at":"2023-02-07T07:13:52.132-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":98365356,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/98365356/thumbnails/1.jpg","file_name":"etrij.2017-027920230207-1-1vmw5pm.pdf","download_url":"https://www.academia.edu/attachments/98365356/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"S_2_Net_Machine_reading_comprehension_wi.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/98365356/etrij.2017-027920230207-1-1vmw5pm-libre.pdf?1675786271=\u0026response-content-disposition=attachment%3B+filename%3DS_2_Net_Machine_reading_comprehension_wi.pdf\u0026Expires=1733028036\u0026Signature=XyMY1Na3ppokYVyK4sLa04lSgLXZN8nKpkSK5X9c2A29YbrYPH67~HPKOojtq0I5PfcvA8OjfQCUf~Fr6WKbBkZqPl83inkUdBNrDB94KlE9mb4wmpZTES32qPLylog7gfD4byD0otj6THaQF59VSj75GPS2cUnn4Y~u3awF4TrFFUHDmkuY3fdD7HPG0e9y0TgmG1v6udOJpZ4wWQ5dVpa2ZeEWH44zDLSl0lp1belVGboNRh9z~oMJP00pxpQI8kuDs3Cup4-Cugvcc9uxIgj74j4JKWUhj27q7EsOfYsYxQYJBOcJxj1IhBic3pTfUXWLeHkoF3VA5WzxdXB0oQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"S_2_Net_Machine_reading_comprehension_with_SRU_based_self_matching_networks","translated_slug":"","page_count":12,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":98365356,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/98365356/thumbnails/1.jpg","file_name":"etrij.2017-027920230207-1-1vmw5pm.pdf","download_url":"https://www.academia.edu/attachments/98365356/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"S_2_Net_Machine_reading_comprehension_wi.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/98365356/etrij.2017-027920230207-1-1vmw5pm-libre.pdf?1675786271=\u0026response-content-disposition=attachment%3B+filename%3DS_2_Net_Machine_reading_comprehension_wi.pdf\u0026Expires=1733028036\u0026Signature=XyMY1Na3ppokYVyK4sLa04lSgLXZN8nKpkSK5X9c2A29YbrYPH67~HPKOojtq0I5PfcvA8OjfQCUf~Fr6WKbBkZqPl83inkUdBNrDB94KlE9mb4wmpZTES32qPLylog7gfD4byD0otj6THaQF59VSj75GPS2cUnn4Y~u3awF4TrFFUHDmkuY3fdD7HPG0e9y0TgmG1v6udOJpZ4wWQ5dVpa2ZeEWH44zDLSl0lp1belVGboNRh9z~oMJP00pxpQI8kuDs3Cup4-Cugvcc9uxIgj74j4JKWUhj27q7EsOfYsYxQYJBOcJxj1IhBic3pTfUXWLeHkoF3VA5WzxdXB0oQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":37,"name":"Information Systems","url":"https://www.academia.edu/Documents/in/Information_Systems"},{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":1237788,"name":"Electrical And Electronic Engineering","url":"https://www.academia.edu/Documents/in/Electrical_And_Electronic_Engineering"}],"urls":[{"id":28771719,"url":"https://onlinelibrary.wiley.com/doi/pdf/10.4218/etrij.2017-0279"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="96477143"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/96477143/Dependency_structure_language_model_for_topic_detection_and_tracking"><img alt="Research paper thumbnail of Dependency structure language model for topic detection and tracking" class="work-thumbnail" src="https://attachments.academia-assets.com/98365401/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/96477143/Dependency_structure_language_model_for_topic_detection_and_tracking">Dependency structure language model for topic detection and tracking</a></div><div class="wp-workCard_item"><span>Information Processing &amp; Management</span><span>, 2007</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="4f976a76bafc5842d3c13272d7424da6" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":98365401,"asset_id":96477143,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/98365401/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="96477143"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="96477143"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 96477143; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=96477143]").text(description); $(".js-view-count[data-work-id=96477143]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 96477143; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='96477143']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 96477143, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "4f976a76bafc5842d3c13272d7424da6" } } $('.js-work-strip[data-work-id=96477143]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":96477143,"title":"Dependency structure language model for topic detection and tracking","translated_title":"","metadata":{"publisher":"Elsevier BV","grobid_abstract":"In this paper, we propose a new language model, namely, a dependency structure language model, for topic detection and tracking (TDT) to compensate for weakness of unigram and bigram language models. The dependency structure language model is based on the Chow expansion theory and the dependency parse tree generated by a linguistic parser. So, long-distance dependencies can be naturally captured by the dependency structure language model. We carried out extensive experiments to verify the proposed model on topic tracking and link detection in TDT. In both cases, the dependency structure language models perform better than strong baseline approaches.","publication_date":{"day":null,"month":null,"year":2007,"errors":{}},"publication_name":"Information Processing \u0026amp; Management","grobid_abstract_attachment_id":98365401},"translated_abstract":null,"internal_url":"https://www.academia.edu/96477143/Dependency_structure_language_model_for_topic_detection_and_tracking","translated_internal_url":"","created_at":"2023-02-07T07:13:51.952-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":98365401,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/98365401/thumbnails/1.jpg","file_name":"j.ipm.2006.02.00720230207-1-3er8pv.pdf","download_url":"https://www.academia.edu/attachments/98365401/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Dependency_structure_language_model_for.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/98365401/j.ipm.2006.02.00720230207-1-3er8pv-libre.pdf?1675786271=\u0026response-content-disposition=attachment%3B+filename%3DDependency_structure_language_model_for.pdf\u0026Expires=1733028036\u0026Signature=bCkLzzpjZl4fio0IqPan4R37nKQnA4ovStLzkg7o1mVoJYRqmef~PI3u0RYsbxS8gbLwRzb8EOaxY0VInKFUOA1ROF5rJj9KAAzOa9xjIqs7gEBA47iMpbh9HYAN~r151GuM5ic3eBZStmk7eLb95bSRiNzYh94KdxYa3vkYPMElo83ed4oTq3ijgcUOr2aN3-52mswsAgwQgH5q7roVPBwHbzH1tTjUyajCKZPth4PePGiOxrBioMIe~xendekmUTnceJwSBugExxW-zSBuyz0nzA0p-aMEfgCY-Bj0IdANo39rAVZkMGOcn1FFxox6R5X7QoxbcxyjPrDBTm7ZqQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Dependency_structure_language_model_for_topic_detection_and_tracking","translated_slug":"","page_count":11,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":98365401,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/98365401/thumbnails/1.jpg","file_name":"j.ipm.2006.02.00720230207-1-3er8pv.pdf","download_url":"https://www.academia.edu/attachments/98365401/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Dependency_structure_language_model_for.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/98365401/j.ipm.2006.02.00720230207-1-3er8pv-libre.pdf?1675786271=\u0026response-content-disposition=attachment%3B+filename%3DDependency_structure_language_model_for.pdf\u0026Expires=1733028036\u0026Signature=bCkLzzpjZl4fio0IqPan4R37nKQnA4ovStLzkg7o1mVoJYRqmef~PI3u0RYsbxS8gbLwRzb8EOaxY0VInKFUOA1ROF5rJj9KAAzOa9xjIqs7gEBA47iMpbh9HYAN~r151GuM5ic3eBZStmk7eLb95bSRiNzYh94KdxYa3vkYPMElo83ed4oTq3ijgcUOr2aN3-52mswsAgwQgH5q7roVPBwHbzH1tTjUyajCKZPth4PePGiOxrBioMIe~xendekmUTnceJwSBugExxW-zSBuyz0nzA0p-aMEfgCY-Bj0IdANo39rAVZkMGOcn1FFxox6R5X7QoxbcxyjPrDBTm7ZqQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":37,"name":"Information Systems","url":"https://www.academia.edu/Documents/in/Information_Systems"},{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":464,"name":"Information Retrieval","url":"https://www.academia.edu/Documents/in/Information_Retrieval"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":3268,"name":"Computational Linguistics","url":"https://www.academia.edu/Documents/in/Computational_Linguistics"},{"id":11128,"name":"Information Extraction","url":"https://www.academia.edu/Documents/in/Information_Extraction"},{"id":14493,"name":"Parsing","url":"https://www.academia.edu/Documents/in/Parsing"},{"id":59587,"name":"Library and Information Studies","url":"https://www.academia.edu/Documents/in/Library_and_Information_Studies"},{"id":238516,"name":"Topic Detection and Tracking","url":"https://www.academia.edu/Documents/in/Topic_Detection_and_Tracking"},{"id":297057,"name":"Dependency Parsing","url":"https://www.academia.edu/Documents/in/Dependency_Parsing"},{"id":520672,"name":"Language Model","url":"https://www.academia.edu/Documents/in/Language_Model"},{"id":2467595,"name":"Probabilistic Model","url":"https://www.academia.edu/Documents/in/Probabilistic_Model"},{"id":3516262,"name":"Dependency Grammar","url":"https://www.academia.edu/Documents/in/Dependency_Grammar"},{"id":3806420,"name":"bigram","url":"https://www.academia.edu/Documents/in/bigram"}],"urls":[{"id":28771718,"url":"https://api.elsevier.com/content/article/PII:S0306457306000203?httpAccept=text/xml"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="96477044"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/96477044/Extending_Korean_PropBank_for_Korean_Semantic_Role_Labeling_and_Applying_Domain_Adaptation_Technique"><img alt="Research paper thumbnail of Extending Korean PropBank for Korean Semantic Role Labeling and Applying Domain Adaptation Technique" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/96477044/Extending_Korean_PropBank_for_Korean_Semantic_Role_Labeling_and_Applying_Domain_Adaptation_Technique">Extending Korean PropBank for Korean Semantic Role Labeling and Applying Domain Adaptation Technique</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">1. 서론 의미역 결정(Semantic Role Labeling)은 문장의 각 술 어의 의미와 그 논항들의 의미적인 관계를 결정하는 자 연 언어 처리의 한 단계이다. 의미역 ...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">1. 서론 의미역 결정(Semantic Role Labeling)은 문장의 각 술 어의 의미와 그 논항들의 의미적인 관계를 결정하는 자 연 언어 처리의 한 단계이다. 의미역 결정은 일반적으로 기계 학습에 의해 이루어지게 되며 현재까지 연구가 활 발하게 진행되고 있다. 일반적인 기계 학습 기반의 의미역 결정 시스템은 해당 문장의 술어들을 식별하고 각 술어에 대한 논항들의 의 미역을 결정하여 “누가, 무엇을, 누구에게, 어떻게, 왜”등의 의미 관계를 찾아내는 시스템이다. 예를 들면 그림 1 의 ‘상어는 연골어류에 속하는 물고기이다.’와 같은 텍스트로 된 문장이 주어졌을 때 의미역 결정 시스 템에 의해 ‘속하.01’이라는 술어와 의미역이 달린 술 어의 논항들을 얻게 된다. 여기서 ‘NR’은 의미역이 달 리지 않았음을 뜻하고 ‘ARG1’은 술어 ‘속하.01’의 논항이 된다. 의미역 결정 시스템은 기계 학습에 필요한 많은 양의 말뭉치를 필요로 한다. 의미역 결정 시스템에서 널리 사 용되는 말뭉치로 PropBank[1]가 있으나 이는 영어 의미 역 결정을 위한 말뭉치이기 때문에 한국어에 적용할 수 없다. 이를 해결하기 위해 Korean PropBank[2]가 만들어 졌으나 의미역 부착 말뭉치와 동사 격틀이 영어 PropBank의 1/8 수준에 불과하다. 따라서 본 논문에서는 한국어 Wikipedia에서 추출한 데이터를 이용하여 Korean PropBank를 확장하고자 한다. 의미역 결정 시스템은 크 게 격틀 사전에 기반을 둔 시스템과 말뭉치에 기반을 둔 시스템으로 나눌 수 있으므로[3] Korean PropBank를 확 장하기 위해 본 논문에서는 말뭉치를 늘리는 방법과 격 틀 사전을 확장하는 방법 모두를 고려한다. 일반적인 의미역 결정 시스템은 학습에 사용한 데이터 와 테스트 데이터가 같은 도메인으로 이루어져 있다. 반 면 학습에 사용한 도메인과는 다른 도메인으로 테스트를 할 경우 의미역 결정 시스템 성능이 큰 폭으로 하락됨을 볼 수 있다.[4] 의미역 결정 시스템...</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="96477044"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="96477044"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 96477044; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=96477044]").text(description); $(".js-view-count[data-work-id=96477044]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 96477044; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='96477044']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 96477044, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=96477044]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":96477044,"title":"Extending Korean PropBank for Korean Semantic Role Labeling and Applying Domain Adaptation Technique","translated_title":"","metadata":{"abstract":"1. 서론 의미역 결정(Semantic Role Labeling)은 문장의 각 술 어의 의미와 그 논항들의 의미적인 관계를 결정하는 자 연 언어 처리의 한 단계이다. 의미역 결정은 일반적으로 기계 학습에 의해 이루어지게 되며 현재까지 연구가 활 발하게 진행되고 있다. 일반적인 기계 학습 기반의 의미역 결정 시스템은 해당 문장의 술어들을 식별하고 각 술어에 대한 논항들의 의 미역을 결정하여 “누가, 무엇을, 누구에게, 어떻게, 왜”등의 의미 관계를 찾아내는 시스템이다. 예를 들면 그림 1 의 ‘상어는 연골어류에 속하는 물고기이다.’와 같은 텍스트로 된 문장이 주어졌을 때 의미역 결정 시스 템에 의해 ‘속하.01’이라는 술어와 의미역이 달린 술 어의 논항들을 얻게 된다. 여기서 ‘NR’은 의미역이 달 리지 않았음을 뜻하고 ‘ARG1’은 술어 ‘속하.01’의 논항이 된다. 의미역 결정 시스템은 기계 학습에 필요한 많은 양의 말뭉치를 필요로 한다. 의미역 결정 시스템에서 널리 사 용되는 말뭉치로 PropBank[1]가 있으나 이는 영어 의미 역 결정을 위한 말뭉치이기 때문에 한국어에 적용할 수 없다. 이를 해결하기 위해 Korean PropBank[2]가 만들어 졌으나 의미역 부착 말뭉치와 동사 격틀이 영어 PropBank의 1/8 수준에 불과하다. 따라서 본 논문에서는 한국어 Wikipedia에서 추출한 데이터를 이용하여 Korean PropBank를 확장하고자 한다. 의미역 결정 시스템은 크 게 격틀 사전에 기반을 둔 시스템과 말뭉치에 기반을 둔 시스템으로 나눌 수 있으므로[3] Korean PropBank를 확 장하기 위해 본 논문에서는 말뭉치를 늘리는 방법과 격 틀 사전을 확장하는 방법 모두를 고려한다. 일반적인 의미역 결정 시스템은 학습에 사용한 데이터 와 테스트 데이터가 같은 도메인으로 이루어져 있다. 반 면 학습에 사용한 도메인과는 다른 도메인으로 테스트를 할 경우 의미역 결정 시스템 성능이 큰 폭으로 하락됨을 볼 수 있다.[4] 의미역 결정 시스템...","publication_date":{"day":null,"month":null,"year":2014,"errors":{}}},"translated_abstract":"1. 서론 의미역 결정(Semantic Role Labeling)은 문장의 각 술 어의 의미와 그 논항들의 의미적인 관계를 결정하는 자 연 언어 처리의 한 단계이다. 의미역 결정은 일반적으로 기계 학습에 의해 이루어지게 되며 현재까지 연구가 활 발하게 진행되고 있다. 일반적인 기계 학습 기반의 의미역 결정 시스템은 해당 문장의 술어들을 식별하고 각 술어에 대한 논항들의 의 미역을 결정하여 “누가, 무엇을, 누구에게, 어떻게, 왜”등의 의미 관계를 찾아내는 시스템이다. 예를 들면 그림 1 의 ‘상어는 연골어류에 속하는 물고기이다.’와 같은 텍스트로 된 문장이 주어졌을 때 의미역 결정 시스 템에 의해 ‘속하.01’이라는 술어와 의미역이 달린 술 어의 논항들을 얻게 된다. 여기서 ‘NR’은 의미역이 달 리지 않았음을 뜻하고 ‘ARG1’은 술어 ‘속하.01’의 논항이 된다. 의미역 결정 시스템은 기계 학습에 필요한 많은 양의 말뭉치를 필요로 한다. 의미역 결정 시스템에서 널리 사 용되는 말뭉치로 PropBank[1]가 있으나 이는 영어 의미 역 결정을 위한 말뭉치이기 때문에 한국어에 적용할 수 없다. 이를 해결하기 위해 Korean PropBank[2]가 만들어 졌으나 의미역 부착 말뭉치와 동사 격틀이 영어 PropBank의 1/8 수준에 불과하다. 따라서 본 논문에서는 한국어 Wikipedia에서 추출한 데이터를 이용하여 Korean PropBank를 확장하고자 한다. 의미역 결정 시스템은 크 게 격틀 사전에 기반을 둔 시스템과 말뭉치에 기반을 둔 시스템으로 나눌 수 있으므로[3] Korean PropBank를 확 장하기 위해 본 논문에서는 말뭉치를 늘리는 방법과 격 틀 사전을 확장하는 방법 모두를 고려한다. 일반적인 의미역 결정 시스템은 학습에 사용한 데이터 와 테스트 데이터가 같은 도메인으로 이루어져 있다. 반 면 학습에 사용한 도메인과는 다른 도메인으로 테스트를 할 경우 의미역 결정 시스템 성능이 큰 폭으로 하락됨을 볼 수 있다.[4] 의미역 결정 시스템...","internal_url":"https://www.academia.edu/96477044/Extending_Korean_PropBank_for_Korean_Semantic_Role_Labeling_and_Applying_Domain_Adaptation_Technique","translated_internal_url":"","created_at":"2023-02-07T07:12:42.682-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Extending_Korean_PropBank_for_Korean_Semantic_Role_Labeling_and_Applying_Domain_Adaptation_Technique","translated_slug":"","page_count":null,"language":"ko","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":203500,"name":"Domain Adaptation","url":"https://www.academia.edu/Documents/in/Domain_Adaptation"},{"id":952431,"name":"Korean Cognitive Science","url":"https://www.academia.edu/Documents/in/Korean_Cognitive_Science"},{"id":2064421,"name":"Semantic Role Labeling","url":"https://www.academia.edu/Documents/in/Semantic_Role_Labeling"}],"urls":[{"id":28771675,"url":"http://cs.kangwon.ac.kr/~isl/thesis/2%EC%B0%A8%EB%85%84%EB%8F%84%20%EA%B0%95%EC%9B%90%EB%8C%80/%ED%95%9C%EA%B5%AD%EC%96%B4%20%EC%9D%98%EB%AF%B8%EC%97%AD%20%EA%B2%B0%EC%A0%95%EC%9D%84%20%EC%9C%84%ED%95%9C%20Korean%20PropBank%20%ED%99%95%EC%9E%A5%20%EB%B0%8F%20%EB%8F%84%EB%A9%94%EC%9D%B8%20%EC%A0%81%EC%9D%91%20%EA%B8%B0%EC%88%A0%20%EC%A0%81%EC%9A%A9.pdf"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718953"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/86718953/Easy_Data_Augmentation_for_Improved_Malware_Detection_A_Comparative_Study"><img alt="Research paper thumbnail of Easy Data Augmentation for Improved Malware Detection: A Comparative Study" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/86718953/Easy_Data_Augmentation_for_Improved_Malware_Detection_A_Comparative_Study">Easy Data Augmentation for Improved Malware Detection: A Comparative Study</a></div><div class="wp-workCard_item"><span>2021 IEEE International Conference on Big Data and Smart Computing (BigComp)</span><span>, 2021</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Artificial data generation is important for improving research outcomes when using deep learning....</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">Artificial data generation is important for improving research outcomes when using deep learning. As one of the most popular and promising generative models, the variational auto-encoder (VAE) model generates synthetic data for training classifiers more accurately. Artificial data can be generated also via easy data augmentation (EDA) techniques. EDA is a simple method used to boost the performance of text classification tasks, and unlike generative models such as VAE, it does not require model training. Malware detection is a task of determining whether there is malicious software in the host system and diagnosing the type of attack. Without an appropriate amount of training data, the detection efficiency of malicious programs decreases. In this study, EDA was applied to malware detection, and two artificial data generation methods were compared. Using both methods, artificial training data to be used for malware detection were generated, and the long short-term memory recurrent neural network (LSTM RNN) based malware detection classifier was boosted. Experiment results show that when the synthetic malware sample generated by EDA was added to the training data, the accuracy of LSTM RNN classifier improved by 1.76% as compared to the 0.98% improvement by VAE. In addition, EDA could generate malware training data, without requiring a separate training process, 10 times faster than VAE. Further, we performed extensive ablation studies conducted and suggested parameters for practical use.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718953"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718953"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718953; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718953]").text(description); $(".js-view-count[data-work-id=86718953]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718953; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718953']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718953, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=86718953]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718953,"title":"Easy Data Augmentation for Improved Malware Detection: A Comparative Study","translated_title":"","metadata":{"abstract":"Artificial data generation is important for improving research outcomes when using deep learning. As one of the most popular and promising generative models, the variational auto-encoder (VAE) model generates synthetic data for training classifiers more accurately. Artificial data can be generated also via easy data augmentation (EDA) techniques. EDA is a simple method used to boost the performance of text classification tasks, and unlike generative models such as VAE, it does not require model training. Malware detection is a task of determining whether there is malicious software in the host system and diagnosing the type of attack. Without an appropriate amount of training data, the detection efficiency of malicious programs decreases. In this study, EDA was applied to malware detection, and two artificial data generation methods were compared. Using both methods, artificial training data to be used for malware detection were generated, and the long short-term memory recurrent neural network (LSTM RNN) based malware detection classifier was boosted. Experiment results show that when the synthetic malware sample generated by EDA was added to the training data, the accuracy of LSTM RNN classifier improved by 1.76% as compared to the 0.98% improvement by VAE. In addition, EDA could generate malware training data, without requiring a separate training process, 10 times faster than VAE. Further, we performed extensive ablation studies conducted and suggested parameters for practical use.","publisher":"IEEE","publication_date":{"day":null,"month":null,"year":2021,"errors":{}},"publication_name":"2021 IEEE International Conference on Big Data and Smart Computing (BigComp)"},"translated_abstract":"Artificial data generation is important for improving research outcomes when using deep learning. As one of the most popular and promising generative models, the variational auto-encoder (VAE) model generates synthetic data for training classifiers more accurately. Artificial data can be generated also via easy data augmentation (EDA) techniques. EDA is a simple method used to boost the performance of text classification tasks, and unlike generative models such as VAE, it does not require model training. Malware detection is a task of determining whether there is malicious software in the host system and diagnosing the type of attack. Without an appropriate amount of training data, the detection efficiency of malicious programs decreases. In this study, EDA was applied to malware detection, and two artificial data generation methods were compared. Using both methods, artificial training data to be used for malware detection were generated, and the long short-term memory recurrent neural network (LSTM RNN) based malware detection classifier was boosted. Experiment results show that when the synthetic malware sample generated by EDA was added to the training data, the accuracy of LSTM RNN classifier improved by 1.76% as compared to the 0.98% improvement by VAE. In addition, EDA could generate malware training data, without requiring a separate training process, 10 times faster than VAE. Further, we performed extensive ablation studies conducted and suggested parameters for practical use.","internal_url":"https://www.academia.edu/86718953/Easy_Data_Augmentation_for_Improved_Malware_Detection_A_Comparative_Study","translated_internal_url":"","created_at":"2022-09-15T19:08:50.721-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Easy_Data_Augmentation_for_Improved_Malware_Detection_A_Comparative_Study","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":50154,"name":"Malware","url":"https://www.academia.edu/Documents/in/Malware"}],"urls":[{"id":23885657,"url":"http://xplorestaging.ieee.org/ielx7/9373068/9373070/09373283.pdf?arnumber=9373283"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718952"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/86718952/Korean_Text_Summarization_using_MASS_with_Relative_Position_Representation"><img alt="Research paper thumbnail of Korean Text Summarization using MASS with Relative Position Representation" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/86718952/Korean_Text_Summarization_using_MASS_with_Relative_Position_Representation">Korean Text Summarization using MASS with Relative Position Representation</a></div><div class="wp-workCard_item"><span>Journal of KIISE</span><span>, 2020</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718952"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718952"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718952; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718952]").text(description); $(".js-view-count[data-work-id=86718952]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718952; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718952']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718952, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=86718952]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718952,"title":"Korean Text Summarization using MASS with Relative Position Representation","translated_title":"","metadata":{"publisher":"Korean Institute of Information Scientists and Engineers","publication_date":{"day":null,"month":null,"year":2020,"errors":{}},"publication_name":"Journal of KIISE"},"translated_abstract":null,"internal_url":"https://www.academia.edu/86718952/Korean_Text_Summarization_using_MASS_with_Relative_Position_Representation","translated_internal_url":"","created_at":"2022-09-15T19:08:50.548-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Korean_Text_Summarization_using_MASS_with_Relative_Position_Representation","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":1725616,"name":"Automatic Summarization","url":"https://www.academia.edu/Documents/in/Automatic_Summarization"},{"id":1763882,"name":"Representation Politics","url":"https://www.academia.edu/Documents/in/Representation_Politics"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718951"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/86718951/Named_Entity_Recognition_with_Structural_SVMs_and_Pegasos_algorithm"><img alt="Research paper thumbnail of Named Entity Recognition with Structural SVMs and Pegasos algorithm" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/86718951/Named_Entity_Recognition_with_Structural_SVMs_and_Pegasos_algorithm">Named Entity Recognition with Structural SVMs and Pegasos algorithm</a></div><div class="wp-workCard_item"><span>Korean Journal of Cognitive Science</span><span>, 2010</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Abstract 개체명 인식은 정보 추출의 한 단계로서 정보검색 분야 뿐 아니라 질의응답과 요약 분야에서 매우 유용하게 사용되고 있다. 본 논문에서는 structural Su...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">Abstract 개체명 인식은 정보 추출의 한 단계로서 정보검색 분야 뿐 아니라 질의응답과 요약 분야에서 매우 유용하게 사용되고 있다. 본 논문에서는 structural Support Vector Machines (structural SVMs) 및 수정된 Pegasos 알고리즘을 이용한 한국어 개체명 인식 시스템에 ...</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718951"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718951"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718951; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718951]").text(description); $(".js-view-count[data-work-id=86718951]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718951; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718951']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718951, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=86718951]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718951,"title":"Named Entity Recognition with Structural SVMs and Pegasos algorithm","translated_title":"","metadata":{"abstract":"Abstract 개체명 인식은 정보 추출의 한 단계로서 정보검색 분야 뿐 아니라 질의응답과 요약 분야에서 매우 유용하게 사용되고 있다. 본 논문에서는 structural Support Vector Machines (structural SVMs) 및 수정된 Pegasos 알고리즘을 이용한 한국어 개체명 인식 시스템에 ...","publisher":"The Korean Society for Cognitive Science","publication_date":{"day":null,"month":null,"year":2010,"errors":{}},"publication_name":"Korean Journal of Cognitive Science"},"translated_abstract":"Abstract 개체명 인식은 정보 추출의 한 단계로서 정보검색 분야 뿐 아니라 질의응답과 요약 분야에서 매우 유용하게 사용되고 있다. 본 논문에서는 structural Support Vector Machines (structural SVMs) 및 수정된 Pegasos 알고리즘을 이용한 한국어 개체명 인식 시스템에 ...","internal_url":"https://www.academia.edu/86718951/Named_Entity_Recognition_with_Structural_SVMs_and_Pegasos_algorithm","translated_internal_url":"","created_at":"2022-09-15T19:08:50.374-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Named_Entity_Recognition_with_Structural_SVMs_and_Pegasos_algorithm","translated_slug":"","page_count":null,"language":"ko","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":191289,"name":"Support vector machine","url":"https://www.academia.edu/Documents/in/Support_vector_machine"},{"id":952431,"name":"Korean Cognitive Science","url":"https://www.academia.edu/Documents/in/Korean_Cognitive_Science"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718950"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/86718950/Fine_grained_named_entity_recognition_and_relation_extraction_for_question_answering"><img alt="Research paper thumbnail of Fine-grained named entity recognition and relation extraction for question answering" class="work-thumbnail" src="https://attachments.academia-assets.com/91107832/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/86718950/Fine_grained_named_entity_recognition_and_relation_extraction_for_question_answering">Fine-grained named entity recognition and relation extraction for question answering</a></div><div class="wp-workCard_item"><span>Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '07</span><span>, 2007</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="c48c7f3d024452c033c1d0d6718bedb6" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":91107832,"asset_id":86718950,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/91107832/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718950"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718950"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718950; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718950]").text(description); $(".js-view-count[data-work-id=86718950]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718950; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718950']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718950, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "c48c7f3d024452c033c1d0d6718bedb6" } } $('.js-work-strip[data-work-id=86718950]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718950,"title":"Fine-grained named entity recognition and relation extraction for question answering","translated_title":"","metadata":{"publisher":"ACM Press","publication_date":{"day":null,"month":null,"year":2007,"errors":{}},"publication_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '07"},"translated_abstract":null,"internal_url":"https://www.academia.edu/86718950/Fine_grained_named_entity_recognition_and_relation_extraction_for_question_answering","translated_internal_url":"","created_at":"2022-09-15T19:08:50.140-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":91107832,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107832/thumbnails/1.jpg","file_name":"pryo4wzei8b0qs9hjaxidjg7xn6lmdvf.pdf","download_url":"https://www.academia.edu/attachments/91107832/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Fine_grained_named_entity_recognition_an.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107832/pryo4wzei8b0qs9hjaxidjg7xn6lmdvf-libre.pdf?1663299299=\u0026response-content-disposition=attachment%3B+filename%3DFine_grained_named_entity_recognition_an.pdf\u0026Expires=1733028036\u0026Signature=UT59MfW-vV9p3EphGEHlu5wZqucSyUB~g039kymEfTaT7Hlm8KbSDfErHHsZJV7cLT-2xfV1UPw95vsRYYZFR7h9lqHXN2-xVGf1SMSxAdWSKEHZqh4ecWI4Fh2Vv3VpXw8s06TyZcid3PAVLil3H3L4-UYLFcRHMb4OfXDT26UxfUP4XawXa~VqPV778Speafw~IOLoslHvkcNV-7hiAdO2ptdQZFL6DG8I9jaLbzr8~I5P9IIsww1b0EPKOsgmNxpdtiEv4JkOKTMIVMiXJaXeNZJUnfDcWADMQh1TvQIOuUQuR1ixDtRl5geJtbGLX3hSxbqCDoguy6V2EkVupg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Fine_grained_named_entity_recognition_and_relation_extraction_for_question_answering","translated_slug":"","page_count":2,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":91107832,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107832/thumbnails/1.jpg","file_name":"pryo4wzei8b0qs9hjaxidjg7xn6lmdvf.pdf","download_url":"https://www.academia.edu/attachments/91107832/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Fine_grained_named_entity_recognition_an.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107832/pryo4wzei8b0qs9hjaxidjg7xn6lmdvf-libre.pdf?1663299299=\u0026response-content-disposition=attachment%3B+filename%3DFine_grained_named_entity_recognition_an.pdf\u0026Expires=1733028036\u0026Signature=UT59MfW-vV9p3EphGEHlu5wZqucSyUB~g039kymEfTaT7Hlm8KbSDfErHHsZJV7cLT-2xfV1UPw95vsRYYZFR7h9lqHXN2-xVGf1SMSxAdWSKEHZqh4ecWI4Fh2Vv3VpXw8s06TyZcid3PAVLil3H3L4-UYLFcRHMb4OfXDT26UxfUP4XawXa~VqPV778Speafw~IOLoslHvkcNV-7hiAdO2ptdQZFL6DG8I9jaLbzr8~I5P9IIsww1b0EPKOsgmNxpdtiEv4JkOKTMIVMiXJaXeNZJUnfDcWADMQh1TvQIOuUQuR1ixDtRl5geJtbGLX3hSxbqCDoguy6V2EkVupg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":29205,"name":"Named Entity Recognition","url":"https://www.academia.edu/Documents/in/Named_Entity_Recognition"},{"id":184950,"name":"Question Answering","url":"https://www.academia.edu/Documents/in/Question_Answering"},{"id":188880,"name":"Relation Extraction","url":"https://www.academia.edu/Documents/in/Relation_Extraction"}],"urls":[{"id":23885656,"url":"http://dl.acm.org/ft_gateway.cfm?id=1277915\u0026amp%3Bftid=431583\u0026amp%3Bdwn=1"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718949"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/86718949/Information_gain_and_divergence_based_feature_selection_for_machine_learning_based_text_categorization"><img alt="Research paper thumbnail of Information gain and divergence-based feature selection for machine learning-based text categorization" class="work-thumbnail" src="https://attachments.academia-assets.com/91107834/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/86718949/Information_gain_and_divergence_based_feature_selection_for_machine_learning_based_text_categorization">Information gain and divergence-based feature selection for machine learning-based text categorization</a></div><div class="wp-workCard_item"><span>Information Processing &amp; Management</span><span>, 2006</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="520d8e795f57c2cfd42fb479950b0788" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":91107834,"asset_id":86718949,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/91107834/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718949"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718949"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718949; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718949]").text(description); $(".js-view-count[data-work-id=86718949]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718949; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718949']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718949, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "520d8e795f57c2cfd42fb479950b0788" } } $('.js-work-strip[data-work-id=86718949]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718949,"title":"Information gain and divergence-based feature selection for machine learning-based text categorization","translated_title":"","metadata":{"publisher":"Elsevier BV","grobid_abstract":"Most previous works of feature selection emphasized only the reduction of high dimensionality of the feature space. But in cases where many features are highly redundant with each other, we must utilize other means, for example, more complex dependence models such as Bayesian network classifiers. In this paper, we introduce a new information gain and divergence-based feature selection method for statistical machine learning-based text categorization without relying on more complex dependence models. Our feature selection method strives to reduce redundancy between features while maintaining information gain in selecting appropriate features for text categorization. Empirical results are given on a number of dataset, showing that our feature selection method is more effective than Koller and SahamiÕs method [Koller, D., \u0026 Sahami, M. (1996). Toward optimal feature selection. In Proceedings of ICML-96, 13th international conference on machine learning], which is one of greedy feature selection methods, and conventional information gain which is commonly used in feature selection for text categorization. Moreover, our feature selection method sometimes produces more improvements of conventional machine learning algorithms over support vector machines which are known to give the best classification accuracy.","publication_date":{"day":null,"month":null,"year":2006,"errors":{}},"publication_name":"Information Processing \u0026amp; Management","grobid_abstract_attachment_id":91107834},"translated_abstract":null,"internal_url":"https://www.academia.edu/86718949/Information_gain_and_divergence_based_feature_selection_for_machine_learning_based_text_categorization","translated_internal_url":"","created_at":"2022-09-15T19:08:49.815-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":91107834,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107834/thumbnails/1.jpg","file_name":"feature_20selection.pdf","download_url":"https://www.academia.edu/attachments/91107834/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Information_gain_and_divergence_based_fe.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107834/feature_20selection-libre.pdf?1663299302=\u0026response-content-disposition=attachment%3B+filename%3DInformation_gain_and_divergence_based_fe.pdf\u0026Expires=1733028036\u0026Signature=f2e-DctCwrgrhFJffc8YvacZ60WotQxjtnMkmYNZn8zNXK2gg5DuJozm906scYd~hcbaJgz9ygVG6py3gWXKU88B~5-hMwmg4XzvJiIfSHD2feZGKKsXSlJ9NIfGzKurBQSd6qVLCWIZFdZWkRYFPjdplurxefhWUwyri28KOlAOT7~X1EvC4QdcTroyIU0CSLareGcHg99gfH~iDorWey8PJtMYwmwBDMUk62Cd810ypPhY1l8gilhGtHWO~JDLqR7m04UfEM8kUPvBCsxy4bB3rebrs~xnwBMX-~2UUL~KbgoVwhT9fr742ypNmA9svwK9K4N5xQmoy5awtc9VAg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Information_gain_and_divergence_based_feature_selection_for_machine_learning_based_text_categorization","translated_slug":"","page_count":11,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":91107834,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107834/thumbnails/1.jpg","file_name":"feature_20selection.pdf","download_url":"https://www.academia.edu/attachments/91107834/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Information_gain_and_divergence_based_fe.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107834/feature_20selection-libre.pdf?1663299302=\u0026response-content-disposition=attachment%3B+filename%3DInformation_gain_and_divergence_based_fe.pdf\u0026Expires=1733028036\u0026Signature=f2e-DctCwrgrhFJffc8YvacZ60WotQxjtnMkmYNZn8zNXK2gg5DuJozm906scYd~hcbaJgz9ygVG6py3gWXKU88B~5-hMwmg4XzvJiIfSHD2feZGKKsXSlJ9NIfGzKurBQSd6qVLCWIZFdZWkRYFPjdplurxefhWUwyri28KOlAOT7~X1EvC4QdcTroyIU0CSLareGcHg99gfH~iDorWey8PJtMYwmwBDMUk62Cd810ypPhY1l8gilhGtHWO~JDLqR7m04UfEM8kUPvBCsxy4bB3rebrs~xnwBMX-~2UUL~KbgoVwhT9fr742ypNmA9svwK9K4N5xQmoy5awtc9VAg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":37,"name":"Information Systems","url":"https://www.academia.edu/Documents/in/Information_Systems"},{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":2008,"name":"Machine Learning","url":"https://www.academia.edu/Documents/in/Machine_Learning"},{"id":18573,"name":"Categorization","url":"https://www.academia.edu/Documents/in/Categorization"},{"id":43619,"name":"Feature Selection","url":"https://www.academia.edu/Documents/in/Feature_Selection"},{"id":47555,"name":"Dimensionality Reduction","url":"https://www.academia.edu/Documents/in/Dimensionality_Reduction"},{"id":59587,"name":"Library and Information Studies","url":"https://www.academia.edu/Documents/in/Library_and_Information_Studies"},{"id":124340,"name":"Text Categorization","url":"https://www.academia.edu/Documents/in/Text_Categorization"}],"urls":[{"id":23885655,"url":"https://api.elsevier.com/content/article/PII:S0306457304000962?httpAccept=text/xml"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718948"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/86718948/A_Multi_Strategic_Concept_Spotting_Approach_for_Robust_Understanding_of_Spoken_Korean"><img alt="Research paper thumbnail of A Multi-Strategic Concept-Spotting Approach for Robust Understanding of Spoken Korean" class="work-thumbnail" src="https://attachments.academia-assets.com/91107831/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/86718948/A_Multi_Strategic_Concept_Spotting_Approach_for_Robust_Understanding_of_Spoken_Korean">A Multi-Strategic Concept-Spotting Approach for Robust Understanding of Spoken Korean</a></div><div class="wp-workCard_item"><span>ETRI Journal</span><span>, 2007</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="aedf55a04090765162d103090b8d11ab" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":91107831,"asset_id":86718948,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/91107831/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718948"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718948"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718948; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718948]").text(description); $(".js-view-count[data-work-id=86718948]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718948; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718948']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718948, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "aedf55a04090765162d103090b8d11ab" } } $('.js-work-strip[data-work-id=86718948]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718948,"title":"A Multi-Strategic Concept-Spotting Approach for Robust Understanding of Spoken Korean","translated_title":"","metadata":{"publisher":"Wiley-Blackwell","publication_date":{"day":null,"month":null,"year":2007,"errors":{}},"publication_name":"ETRI Journal"},"translated_abstract":null,"internal_url":"https://www.academia.edu/86718948/A_Multi_Strategic_Concept_Spotting_Approach_for_Robust_Understanding_of_Spoken_Korean","translated_internal_url":"","created_at":"2022-09-15T19:08:49.656-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":91107831,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107831/thumbnails/1.jpg","file_name":"ff01038f3ce5177c98ccc058160dcfe0e08e.pdf","download_url":"https://www.academia.edu/attachments/91107831/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"A_Multi_Strategic_Concept_Spotting_Appro.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107831/ff01038f3ce5177c98ccc058160dcfe0e08e-libre.pdf?1663299302=\u0026response-content-disposition=attachment%3B+filename%3DA_Multi_Strategic_Concept_Spotting_Appro.pdf\u0026Expires=1733028036\u0026Signature=KPmd4kdb2dJTIK5QqelGpRhEZBfbqbkHK~DBAfYjK8QVV0FsWbaw6K8ANa0jPYUmGeSYhobEzGSpPTGfkhJ6AkQjLZ3vSjJNgxNrx8oZwSARn9EtYRzhsUj3kE-n4fM3QlD01bLVHVvlA7cORpqjIj8KBfilcc4oxwBI8mD9~kzxPJe5PBoR3oBNuuMqP-MvkLZmeRLj5qLhpj7Ih2LVrvBdisaKprSqK6cNB8V5fzk4tNj8rBXIcoQFrCxS6mQv13OetQlzlKmFn0ZNDdwmUJDDavC7yXMQlSOAlE6bTFNUu-p~cMs4ipKekU6qjuBr4hc58UUXPgiOdxYF329H7Q__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"A_Multi_Strategic_Concept_Spotting_Approach_for_Robust_Understanding_of_Spoken_Korean","translated_slug":"","page_count":10,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":91107831,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107831/thumbnails/1.jpg","file_name":"ff01038f3ce5177c98ccc058160dcfe0e08e.pdf","download_url":"https://www.academia.edu/attachments/91107831/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"A_Multi_Strategic_Concept_Spotting_Appro.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107831/ff01038f3ce5177c98ccc058160dcfe0e08e-libre.pdf?1663299302=\u0026response-content-disposition=attachment%3B+filename%3DA_Multi_Strategic_Concept_Spotting_Appro.pdf\u0026Expires=1733028036\u0026Signature=KPmd4kdb2dJTIK5QqelGpRhEZBfbqbkHK~DBAfYjK8QVV0FsWbaw6K8ANa0jPYUmGeSYhobEzGSpPTGfkhJ6AkQjLZ3vSjJNgxNrx8oZwSARn9EtYRzhsUj3kE-n4fM3QlD01bLVHVvlA7cORpqjIj8KBfilcc4oxwBI8mD9~kzxPJe5PBoR3oBNuuMqP-MvkLZmeRLj5qLhpj7Ih2LVrvBdisaKprSqK6cNB8V5fzk4tNj8rBXIcoQFrCxS6mQv13OetQlzlKmFn0ZNDdwmUJDDavC7yXMQlSOAlE6bTFNUu-p~cMs4ipKekU6qjuBr4hc58UUXPgiOdxYF329H7Q__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":37,"name":"Information Systems","url":"https://www.academia.edu/Documents/in/Information_Systems"},{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":11128,"name":"Information Extraction","url":"https://www.academia.edu/Documents/in/Information_Extraction"},{"id":102864,"name":"Spoken language","url":"https://www.academia.edu/Documents/in/Spoken_language"},{"id":119709,"name":"Spontaneous speech","url":"https://www.academia.edu/Documents/in/Spontaneous_speech"},{"id":151727,"name":"Keyword Spotting","url":"https://www.academia.edu/Documents/in/Keyword_Spotting"},{"id":1237788,"name":"Electrical And Electronic Engineering","url":"https://www.academia.edu/Documents/in/Electrical_And_Electronic_Engineering"},{"id":1763882,"name":"Representation Politics","url":"https://www.academia.edu/Documents/in/Representation_Politics"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718947"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/86718947/Dependency_Structure_Applied_to_Language_Modeling_for_Information_Retrieval"><img alt="Research paper thumbnail of Dependency Structure Applied to Language Modeling for Information Retrieval" class="work-thumbnail" src="https://attachments.academia-assets.com/91107833/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/86718947/Dependency_Structure_Applied_to_Language_Modeling_for_Information_Retrieval">Dependency Structure Applied to Language Modeling for Information Retrieval</a></div><div class="wp-workCard_item"><span>ETRI Journal</span><span>, 2006</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="0023d0f23b53acfbd4066798fd36ff95" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":91107833,"asset_id":86718947,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/91107833/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718947"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718947"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718947; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718947]").text(description); $(".js-view-count[data-work-id=86718947]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718947; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718947']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718947, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "0023d0f23b53acfbd4066798fd36ff95" } } $('.js-work-strip[data-work-id=86718947]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718947,"title":"Dependency Structure Applied to Language Modeling for Information Retrieval","translated_title":"","metadata":{"publisher":"Wiley","grobid_abstract":"In this paper, we propose a new language model, namely, a dependency structure language model, for information retrieval to compensate for the weaknesses of unigram and bigram language models. The dependency structure language model is based on the first-order dependency model and the dependency parse tree generated by a linguistic parser. So, long-distance dependencies can be naturally captured by the dependency structure language model. We carried out extensive experiments to verify the proposed model, where the dependency structure model gives a better performance than recently proposed language models and the Okapi BM25 method, and the dependency structure is more effective than unigram and bigram in language modeling for information retrieval.","publication_date":{"day":null,"month":null,"year":2006,"errors":{}},"publication_name":"ETRI Journal","grobid_abstract_attachment_id":91107833},"translated_abstract":null,"internal_url":"https://www.academia.edu/86718947/Dependency_Structure_Applied_to_Language_Modeling_for_Information_Retrieval","translated_internal_url":"","created_at":"2022-09-15T19:08:49.436-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":91107833,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107833/thumbnails/1.jpg","file_name":"HJTODO_2006_v28n3_337.pdf","download_url":"https://www.academia.edu/attachments/91107833/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Dependency_Structure_Applied_to_Language.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107833/HJTODO_2006_v28n3_337-libre.pdf?1663299307=\u0026response-content-disposition=attachment%3B+filename%3DDependency_Structure_Applied_to_Language.pdf\u0026Expires=1733028036\u0026Signature=Rv0OlY2TOJSUBiLtZeX2a~IhsiMWhZ2tVaPs3rYVwI350-~S7eNmuqR0iQ615zKNHs-~HsSeV3V6VxEpD-hCJdFXausMHMfO89-gJBTp3wKSjh8cyUGLmQ0ZL817DlBclYSxNrPZhqPu3QJ4PTOXmL8G5fFTr04~RGwz7H7~u7LfnPEXVVEA-BDfErIGWliw3TS9XRN54u6lQUvI~FpJ8Iun8hNBITD--9cLchDTDMO8UJTitp5b5mt0y98YBwYwOKAqoKSjvH01j0Yqz7hvUwCAi3~0nmWZP8Oc~ezy~35oyj7PP3XhtgiOf00zoSdkcdcHqsoUFtCcvUi~fBEGow__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Dependency_Structure_Applied_to_Language_Modeling_for_Information_Retrieval","translated_slug":"","page_count":10,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":91107833,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107833/thumbnails/1.jpg","file_name":"HJTODO_2006_v28n3_337.pdf","download_url":"https://www.academia.edu/attachments/91107833/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Dependency_Structure_Applied_to_Language.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107833/HJTODO_2006_v28n3_337-libre.pdf?1663299307=\u0026response-content-disposition=attachment%3B+filename%3DDependency_Structure_Applied_to_Language.pdf\u0026Expires=1733028036\u0026Signature=Rv0OlY2TOJSUBiLtZeX2a~IhsiMWhZ2tVaPs3rYVwI350-~S7eNmuqR0iQ615zKNHs-~HsSeV3V6VxEpD-hCJdFXausMHMfO89-gJBTp3wKSjh8cyUGLmQ0ZL817DlBclYSxNrPZhqPu3QJ4PTOXmL8G5fFTr04~RGwz7H7~u7LfnPEXVVEA-BDfErIGWliw3TS9XRN54u6lQUvI~FpJ8Iun8hNBITD--9cLchDTDMO8UJTitp5b5mt0y98YBwYwOKAqoKSjvH01j0Yqz7hvUwCAi3~0nmWZP8Oc~ezy~35oyj7PP3XhtgiOf00zoSdkcdcHqsoUFtCcvUi~fBEGow__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":37,"name":"Information Systems","url":"https://www.academia.edu/Documents/in/Information_Systems"},{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":1237788,"name":"Electrical And Electronic Engineering","url":"https://www.academia.edu/Documents/in/Electrical_And_Electronic_Engineering"}],"urls":[{"id":23885654,"url":"https://etrij.etri.re.kr/etrij/journal/getPublishedPaperFile.do?fileId=SPF-1149841527877"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="86718918"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/86718918/Net_Korean_Machine_Reading_Comprehension_using_SRU_based_Sentence_and_Self_Matching_Networks"><img alt="Research paper thumbnail of Net : Korean Machine Reading Comprehension using SRU-based Sentence and Self Matching Networks" class="work-thumbnail" src="https://attachments.academia-assets.com/91107777/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/86718918/Net_Korean_Machine_Reading_Comprehension_using_SRU_based_Sentence_and_Self_Matching_Networks">Net : Korean Machine Reading Comprehension using SRU-based Sentence and Self Matching Networks</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">셋에서 기존의 S-Net보다 우수한 (dev) EM 70.08%, F1 81.78%, (test) EM 69.43%, F1 81.53%의 성능을 보였다. 1. 서 론 기계 독...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">셋에서 기존의 S-Net보다 우수한 (dev) EM 70.08%, F1 81.78%, (test) EM 69.43%, F1 81.53%의 성능을 보였다. 1. 서 론 기계 독해를 이용한 질의 응답(Question Answering)은 페이스북 bAbi task의 CBT와 같이 주어진 문맥에서 빈칸을 채우는 cloze 스타일과 주 어진 문맥에서 정답이 포함된 문장을 찾는 WikiQA, 주어진 문맥에서 정답의 시작과 끝 경계를 찾는 스탠포드의 SQuAD등과 같은 문제들로 나뉘며, 좀더 복합적인 문제로 마이크로소프트의 MS-MARCO가 있다 [1, 2, 3, 4]. 위와 같은 문제를 해결하기 위해서는 기계가 주어진 문맥을 이해하고 문맥 내에서 정답을 찾아야 하는데, 이처럼 기계가 주어진 문 장을 이해하는 것을 기계 독해(Machine Reading Comprehension)라 한 다. 예를 들어, 기계 독해 시스템은 “국내 건조기 시장 점유율 1위 누구 야?”와 같은 질문에 대하여, 문맥 “2004년 건조기 시장에 ... 의류 건조 기 중 LG전자는 점유율 77.4%로 1위를 차지했다.”를 이해하고, 해당 문맥 내에서 정답 “LG전자”를 찾아 출력한다. 기계 독해 문제를 해결하기 위하여 S2-Net, DrQA, fastQA, RNet, Bi-Directional Flow (BiDAF) 등[5-9]과 같은 end-to-end 딥 러 닝 모델들이 연구되고 있으며, 이러한 모델들은 주어진 질문과 문 맥에 대하여 매칭과 인코딩을 수행하고, 질문과 문맥을 매칭하고, 어텐션 매커니즘(attention mechanism)[10]을 기반으로 한 포인터 네트워크(Pointer Networks)[11]로 질문과 유사한 정답의 경계 인 덱스(즉, 정답의 시작과 끝 위치)를 출력한다. 본 논문의 선행 연 구인 S2-Net은 한국어 기계 독해 데이터셋인 MindsMRC에서 질 의응답을 적용하였으며, 이때 주어진 하나의 문단은 여러 문장으</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="c287d5654c30bdae68f21c5f0f25a99e" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":91107777,"asset_id":86718918,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/91107777/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="86718918"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="86718918"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 86718918; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=86718918]").text(description); $(".js-view-count[data-work-id=86718918]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 86718918; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='86718918']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 86718918, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "c287d5654c30bdae68f21c5f0f25a99e" } } $('.js-work-strip[data-work-id=86718918]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":86718918,"title":"Net : Korean Machine Reading Comprehension using SRU-based Sentence and Self Matching Networks","translated_title":"","metadata":{"abstract":"셋에서 기존의 S-Net보다 우수한 (dev) EM 70.08%, F1 81.78%, (test) EM 69.43%, F1 81.53%의 성능을 보였다. 1. 서 론 기계 독해를 이용한 질의 응답(Question Answering)은 페이스북 bAbi task의 CBT와 같이 주어진 문맥에서 빈칸을 채우는 cloze 스타일과 주 어진 문맥에서 정답이 포함된 문장을 찾는 WikiQA, 주어진 문맥에서 정답의 시작과 끝 경계를 찾는 스탠포드의 SQuAD등과 같은 문제들로 나뉘며, 좀더 복합적인 문제로 마이크로소프트의 MS-MARCO가 있다 [1, 2, 3, 4]. 위와 같은 문제를 해결하기 위해서는 기계가 주어진 문맥을 이해하고 문맥 내에서 정답을 찾아야 하는데, 이처럼 기계가 주어진 문 장을 이해하는 것을 기계 독해(Machine Reading Comprehension)라 한 다. 예를 들어, 기계 독해 시스템은 “국내 건조기 시장 점유율 1위 누구 야?”와 같은 질문에 대하여, 문맥 “2004년 건조기 시장에 ... 의류 건조 기 중 LG전자는 점유율 77.4%로 1위를 차지했다.”를 이해하고, 해당 문맥 내에서 정답 “LG전자”를 찾아 출력한다. 기계 독해 문제를 해결하기 위하여 S2-Net, DrQA, fastQA, RNet, Bi-Directional Flow (BiDAF) 등[5-9]과 같은 end-to-end 딥 러 닝 모델들이 연구되고 있으며, 이러한 모델들은 주어진 질문과 문 맥에 대하여 매칭과 인코딩을 수행하고, 질문과 문맥을 매칭하고, 어텐션 매커니즘(attention mechanism)[10]을 기반으로 한 포인터 네트워크(Pointer Networks)[11]로 질문과 유사한 정답의 경계 인 덱스(즉, 정답의 시작과 끝 위치)를 출력한다. 본 논문의 선행 연 구인 S2-Net은 한국어 기계 독해 데이터셋인 MindsMRC에서 질 의응답을 적용하였으며, 이때 주어진 하나의 문단은 여러 문장으","publication_date":{"day":null,"month":null,"year":2017,"errors":{}}},"translated_abstract":"셋에서 기존의 S-Net보다 우수한 (dev) EM 70.08%, F1 81.78%, (test) EM 69.43%, F1 81.53%의 성능을 보였다. 1. 서 론 기계 독해를 이용한 질의 응답(Question Answering)은 페이스북 bAbi task의 CBT와 같이 주어진 문맥에서 빈칸을 채우는 cloze 스타일과 주 어진 문맥에서 정답이 포함된 문장을 찾는 WikiQA, 주어진 문맥에서 정답의 시작과 끝 경계를 찾는 스탠포드의 SQuAD등과 같은 문제들로 나뉘며, 좀더 복합적인 문제로 마이크로소프트의 MS-MARCO가 있다 [1, 2, 3, 4]. 위와 같은 문제를 해결하기 위해서는 기계가 주어진 문맥을 이해하고 문맥 내에서 정답을 찾아야 하는데, 이처럼 기계가 주어진 문 장을 이해하는 것을 기계 독해(Machine Reading Comprehension)라 한 다. 예를 들어, 기계 독해 시스템은 “국내 건조기 시장 점유율 1위 누구 야?”와 같은 질문에 대하여, 문맥 “2004년 건조기 시장에 ... 의류 건조 기 중 LG전자는 점유율 77.4%로 1위를 차지했다.”를 이해하고, 해당 문맥 내에서 정답 “LG전자”를 찾아 출력한다. 기계 독해 문제를 해결하기 위하여 S2-Net, DrQA, fastQA, RNet, Bi-Directional Flow (BiDAF) 등[5-9]과 같은 end-to-end 딥 러 닝 모델들이 연구되고 있으며, 이러한 모델들은 주어진 질문과 문 맥에 대하여 매칭과 인코딩을 수행하고, 질문과 문맥을 매칭하고, 어텐션 매커니즘(attention mechanism)[10]을 기반으로 한 포인터 네트워크(Pointer Networks)[11]로 질문과 유사한 정답의 경계 인 덱스(즉, 정답의 시작과 끝 위치)를 출력한다. 본 논문의 선행 연 구인 S2-Net은 한국어 기계 독해 데이터셋인 MindsMRC에서 질 의응답을 적용하였으며, 이때 주어진 하나의 문단은 여러 문장으","internal_url":"https://www.academia.edu/86718918/Net_Korean_Machine_Reading_Comprehension_using_SRU_based_Sentence_and_Self_Matching_Networks","translated_internal_url":"","created_at":"2022-09-15T19:07:31.360-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":91107777,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107777/thumbnails/1.jpg","file_name":"SRU_20_EA_B8_B0_EB_B0_98_20_EB_AC_B8_EC_9E_A5_20_EB_B0_8F_20_EC_85_80_ED_94_84_20_EB_A7_A4_EC_B9_AD_20_EB_84_A4_ED_8A_B8_EC_9B_8C_ED_81_.pdf","download_url":"https://www.academia.edu/attachments/91107777/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Net_Korean_Machine_Reading_Comprehension.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107777/SRU_20_EA_B8_B0_EB_B0_98_20_EB_AC_B8_EC_9E_A5_20_EB_B0_8F_20_EC_85_80_ED_94_84_20_EB_A7_A4_EC_B9_AD_20_EB_84_A4_ED_8A_B8_EC_9B_8C_ED_81_-libre.pdf?1663299315=\u0026response-content-disposition=attachment%3B+filename%3DNet_Korean_Machine_Reading_Comprehension.pdf\u0026Expires=1732979528\u0026Signature=F7m3odfyZT3dQFGKYcP3bgC-8~W-a9g0HR1eSm9LkaweSUlPpgWBWW9Hjl1dbl7NfDf4lZ0DuDOelLshXSlMl5xTSe0g~ZrdjDe0x5zR-nCUKLDVz12C1xDQMCtQ~VD28Q3Ec8tYuvexWQlEN1YabSHuBVfbHux2ljdzVhJvtqZIzkP3ZN0D2eoqc13lr7A4DAfSJ4wwF37otar42f6EKfdB88rmNzFjfO2c0HOjAVC4w6iY3wiNNDpyy8IgZkKYl2TAiSJ8tHEp2s8fSX1eG1IeGggCe-XEhkf0y8o66fxD-UaBnKcnAExVqRXEyZf5-XZ1Ln5OZ3~9bJwmbVnrBQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Net_Korean_Machine_Reading_Comprehension_using_SRU_based_Sentence_and_Self_Matching_Networks","translated_slug":"","page_count":3,"language":"ko","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":91107777,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107777/thumbnails/1.jpg","file_name":"SRU_20_EA_B8_B0_EB_B0_98_20_EB_AC_B8_EC_9E_A5_20_EB_B0_8F_20_EC_85_80_ED_94_84_20_EB_A7_A4_EC_B9_AD_20_EB_84_A4_ED_8A_B8_EC_9B_8C_ED_81_.pdf","download_url":"https://www.academia.edu/attachments/91107777/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Net_Korean_Machine_Reading_Comprehension.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107777/SRU_20_EA_B8_B0_EB_B0_98_20_EB_AC_B8_EC_9E_A5_20_EB_B0_8F_20_EC_85_80_ED_94_84_20_EB_A7_A4_EC_B9_AD_20_EB_84_A4_ED_8A_B8_EC_9B_8C_ED_81_-libre.pdf?1663299315=\u0026response-content-disposition=attachment%3B+filename%3DNet_Korean_Machine_Reading_Comprehension.pdf\u0026Expires=1732979528\u0026Signature=F7m3odfyZT3dQFGKYcP3bgC-8~W-a9g0HR1eSm9LkaweSUlPpgWBWW9Hjl1dbl7NfDf4lZ0DuDOelLshXSlMl5xTSe0g~ZrdjDe0x5zR-nCUKLDVz12C1xDQMCtQ~VD28Q3Ec8tYuvexWQlEN1YabSHuBVfbHux2ljdzVhJvtqZIzkP3ZN0D2eoqc13lr7A4DAfSJ4wwF37otar42f6EKfdB88rmNzFjfO2c0HOjAVC4w6iY3wiNNDpyy8IgZkKYl2TAiSJ8tHEp2s8fSX1eG1IeGggCe-XEhkf0y8o66fxD-UaBnKcnAExVqRXEyZf5-XZ1Ln5OZ3~9bJwmbVnrBQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"},{"id":91107776,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/91107776/thumbnails/1.jpg","file_name":"SRU_20_EA_B8_B0_EB_B0_98_20_EB_AC_B8_EC_9E_A5_20_EB_B0_8F_20_EC_85_80_ED_94_84_20_EB_A7_A4_EC_B9_AD_20_EB_84_A4_ED_8A_B8_EC_9B_8C_ED_81_.pdf","download_url":"https://www.academia.edu/attachments/91107776/download_file","bulk_download_file_name":"Net_Korean_Machine_Reading_Comprehension.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/91107776/SRU_20_EA_B8_B0_EB_B0_98_20_EB_AC_B8_EC_9E_A5_20_EB_B0_8F_20_EC_85_80_ED_94_84_20_EB_A7_A4_EC_B9_AD_20_EB_84_A4_ED_8A_B8_EC_9B_8C_ED_81_-libre.pdf?1663299314=\u0026response-content-disposition=attachment%3B+filename%3DNet_Korean_Machine_Reading_Comprehension.pdf\u0026Expires=1732979528\u0026Signature=HGfVD6aYXrQL4jIxRkL5x5XhB3bjNR5kXE2AP2hX73otbeQ5ZBuC2DXFSAeSI9kabsv7XbzlmARXOadh7PZrZHE3F~qT3cW8yOCE~jy0zXomX8bsRbT~0XPAPo9ZsXRtoEe~On~zjEEPopClGGDm5oGjejy9VSmFIdrAWufZFMyLzAYEULP-dgYr~34XLnF1t8xSLfpBvbFC0Niygy3aOupph9oeM~xFBGUH5tQpVOkfYZ469pxaHsl4R6Ux4zecbRdpdXrbq1YErMoSIHIFjVNh~cbq60l5wffyGlvji~exq44OJlz4t4dsA2jsc0xI23JzvVqllEms2O7IrPs2Rg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[],"urls":[{"id":23885638,"url":"http://cs.kangwon.ac.kr/~isl/thesis/%EB%85%BC%EB%AC%B8/SRU%20%EA%B8%B0%EB%B0%98%20%EB%AC%B8%EC%9E%A5%20%EB%B0%8F%20%EC%85%80%ED%94%84%20%EB%A7%A4%EC%B9%AD%20%EB%84%A4%ED%8A%B8%EC%9B%8C%ED%81%AC%EB%A5%BC%20%EC%9D%B4%EC%9A%A9%ED%95%9C%20%ED%95%9C%EA%B5%AD%EC%96%B4%20%EA%B8%B0%EA%B3%84%EB%8F%85%ED%95%B4.pdf"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="82772018"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/82772018/Structural_SVM%EC%9D%84_%EC%9D%B4%EC%9A%A9%ED%95%9C_%ED%95%9C%EA%B5%AD%EC%96%B4_%EB%9D%84%EC%96%B4%EC%93%B0%EA%B8%B0_%EB%B0%8F_%ED%92%88%EC%82%AC_%ED%83%9C%EA%B9%85_%EA%B2%B0%ED%95%A9_%EB%AA%A8%EB%8D%B8_Joint_Models_for_Korean_Word_Spacing_and_POS_Tagging_using_Structural_SVM_"><img alt="Research paper thumbnail of Structural SVM을 이용한 한국어 띄어쓰기 및 품사 태깅 결합 모델 (Joint Models for Korean Word Spacing and POS Tagging using Structural SVM)" class="work-thumbnail" src="https://attachments.academia-assets.com/88368653/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/82772018/Structural_SVM%EC%9D%84_%EC%9D%B4%EC%9A%A9%ED%95%9C_%ED%95%9C%EA%B5%AD%EC%96%B4_%EB%9D%84%EC%96%B4%EC%93%B0%EA%B8%B0_%EB%B0%8F_%ED%92%88%EC%82%AC_%ED%83%9C%EA%B9%85_%EA%B2%B0%ED%95%A9_%EB%AA%A8%EB%8D%B8_Joint_Models_for_Korean_Word_Spacing_and_POS_Tagging_using_Structural_SVM_">Structural SVM을 이용한 한국어 띄어쓰기 및 품사 태깅 결합 모델 (Joint Models for Korean Word Spacing and POS Tagging using Structural SVM)</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Typically, a Korean Part-of-speech (POS) tagger takes the inputs that are produced by a separate ...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">Typically, a Korean Part-of-speech (POS) tagger takes the inputs that are produced by a separate Korean word spacer. However this pipeline approach has an obvious flaw of error propagation, since the POS tagger cannot correct word spacing errors. In this paper, we describe a joint model for Korean word spacing and POS tagging using structural SVM to avoid error propagation and improve word spacing by utilizing POS information. In the case of a pipeline approach, we could achieve a 96.77% morpheme-based F-measure for POS tagging. Using the joint model, we could achieve a 96.99% morpheme-based F-measure for POS tagging. Experimental results show that the joint model outperforms the pipeline approach. ․본 연구는 미래창조과학부 및 한국산업기술평가관리원의 산업융합원천기 술개발사업(정보통신) [10044577, 휴먼 지식증강 서비스를 위한 지능진 화형 WiseQA 플랫폼 기술 개발]과 [2013년도 강원대 전임교원 기본연구 비(하반기)] 사업의 일환으로 수행하였음 ․이 논문은 2013 한국컴퓨터종합학술대회에서 &#39;Structural SVM을 이용한 한국어 띄어쓰기 및 품사 태깅 결합 모델&#39;의 제목으로 발표된 논문을 확장 한 것임 † 종신회원 논문접수 심사완료 : : : 강원대학교 컴퓨터과학과 교수 l...</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="bb0bc7c25f5e780879346908becf0d03" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":88368653,"asset_id":82772018,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/88368653/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="82772018"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="82772018"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 82772018; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=82772018]").text(description); $(".js-view-count[data-work-id=82772018]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 82772018; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='82772018']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 82772018, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "bb0bc7c25f5e780879346908becf0d03" } } $('.js-work-strip[data-work-id=82772018]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":82772018,"title":"Structural SVM을 이용한 한국어 띄어쓰기 및 품사 태깅 결합 모델 (Joint Models for Korean Word Spacing and POS Tagging using Structural SVM)","translated_title":"","metadata":{"abstract":"Typically, a Korean Part-of-speech (POS) tagger takes the inputs that are produced by a separate Korean word spacer. However this pipeline approach has an obvious flaw of error propagation, since the POS tagger cannot correct word spacing errors. In this paper, we describe a joint model for Korean word spacing and POS tagging using structural SVM to avoid error propagation and improve word spacing by utilizing POS information. In the case of a pipeline approach, we could achieve a 96.77% morpheme-based F-measure for POS tagging. Using the joint model, we could achieve a 96.99% morpheme-based F-measure for POS tagging. Experimental results show that the joint model outperforms the pipeline approach. ․본 연구는 미래창조과학부 및 한국산업기술평가관리원의 산업융합원천기 술개발사업(정보통신) [10044577, 휴먼 지식증강 서비스를 위한 지능진 화형 WiseQA 플랫폼 기술 개발]과 [2013년도 강원대 전임교원 기본연구 비(하반기)] 사업의 일환으로 수행하였음 ․이 논문은 2013 한국컴퓨터종합학술대회에서 \u0026#39;Structural SVM을 이용한 한국어 띄어쓰기 및 품사 태깅 결합 모델\u0026#39;의 제목으로 발표된 논문을 확장 한 것임 † 종신회원 논문접수 심사완료 : : : 강원대학교 컴퓨터과학과 교수 l..."},"translated_abstract":"Typically, a Korean Part-of-speech (POS) tagger takes the inputs that are produced by a separate Korean word spacer. However this pipeline approach has an obvious flaw of error propagation, since the POS tagger cannot correct word spacing errors. In this paper, we describe a joint model for Korean word spacing and POS tagging using structural SVM to avoid error propagation and improve word spacing by utilizing POS information. In the case of a pipeline approach, we could achieve a 96.77% morpheme-based F-measure for POS tagging. Using the joint model, we could achieve a 96.99% morpheme-based F-measure for POS tagging. Experimental results show that the joint model outperforms the pipeline approach. ․본 연구는 미래창조과학부 및 한국산업기술평가관리원의 산업융합원천기 술개발사업(정보통신) [10044577, 휴먼 지식증강 서비스를 위한 지능진 화형 WiseQA 플랫폼 기술 개발]과 [2013년도 강원대 전임교원 기본연구 비(하반기)] 사업의 일환으로 수행하였음 ․이 논문은 2013 한국컴퓨터종합학술대회에서 \u0026#39;Structural SVM을 이용한 한국어 띄어쓰기 및 품사 태깅 결합 모델\u0026#39;의 제목으로 발표된 논문을 확장 한 것임 † 종신회원 논문접수 심사완료 : : : 강원대학교 컴퓨터과학과 교수 l...","internal_url":"https://www.academia.edu/82772018/Structural_SVM%EC%9D%84_%EC%9D%B4%EC%9A%A9%ED%95%9C_%ED%95%9C%EA%B5%AD%EC%96%B4_%EB%9D%84%EC%96%B4%EC%93%B0%EA%B8%B0_%EB%B0%8F_%ED%92%88%EC%82%AC_%ED%83%9C%EA%B9%85_%EA%B2%B0%ED%95%A9_%EB%AA%A8%EB%8D%B8_Joint_Models_for_Korean_Word_Spacing_and_POS_Tagging_using_Structural_SVM_","translated_internal_url":"","created_at":"2022-07-07T21:34:36.387-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":88368653,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368653/thumbnails/1.jpg","file_name":"09.pdf","download_url":"https://www.academia.edu/attachments/88368653/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Structural_SVM.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368653/09-libre.pdf?1657338801=\u0026response-content-disposition=attachment%3B+filename%3DStructural_SVM.pdf\u0026Expires=1733028036\u0026Signature=Pe7eogUmhYg-ZWY0DwLdDhOTv5At4Hw1LGZYnaZA~essu5x3It1zK5zS40POKolxxMwMUE7dwPN9tjttWJ6Y-~cNTi6JPTEZyXo05eOjsSCbACceiNUv6v4IEX37rPGIDMO2veEa6qilca-hk0X-se5kPSI1JH52nNywFcj5HXdM-tnExKbIXsY7coJKoMShPhI4J1-vKD7VEOjrWrS55bZ9UuFJ7uCEG2H2e0eWN9Cu-CgHaDG9jf29LLTDtMWEIGujLyRJe1Xqz9En4Z4JqIQMpSqDrwi7RyesjSNaaAT8Do5ET1RXqNix9l-0Ue2fB~z1Gv-Aogvz6CjgYNrcAA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Structural_SVM을_이용한_한국어_띄어쓰기_및_품사_태깅_결합_모델_Joint_Models_for_Korean_Word_Spacing_and_POS_Tagging_using_Structural_SVM_","translated_slug":"","page_count":7,"language":"ko","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":88368653,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368653/thumbnails/1.jpg","file_name":"09.pdf","download_url":"https://www.academia.edu/attachments/88368653/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Structural_SVM.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368653/09-libre.pdf?1657338801=\u0026response-content-disposition=attachment%3B+filename%3DStructural_SVM.pdf\u0026Expires=1733028036\u0026Signature=Pe7eogUmhYg-ZWY0DwLdDhOTv5At4Hw1LGZYnaZA~essu5x3It1zK5zS40POKolxxMwMUE7dwPN9tjttWJ6Y-~cNTi6JPTEZyXo05eOjsSCbACceiNUv6v4IEX37rPGIDMO2veEa6qilca-hk0X-se5kPSI1JH52nNywFcj5HXdM-tnExKbIXsY7coJKoMShPhI4J1-vKD7VEOjrWrS55bZ9UuFJ7uCEG2H2e0eWN9Cu-CgHaDG9jf29LLTDtMWEIGujLyRJe1Xqz9En4Z4JqIQMpSqDrwi7RyesjSNaaAT8Do5ET1RXqNix9l-0Ue2fB~z1Gv-Aogvz6CjgYNrcAA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[],"urls":[{"id":21998392,"url":"https://web.archive.org/web/20180424232914/http://kiise.or.kr/e_journal/2013/12/sa/pdf/09.pdf"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="82772001"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/82772001/English_to_Korean_Machine_Translation_using_Image_Information"><img alt="Research paper thumbnail of English-to-Korean Machine Translation using Image Information" class="work-thumbnail" src="https://attachments.academia-assets.com/88368182/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/82772001/English_to_Korean_Machine_Translation_using_Image_Information">English-to-Korean Machine Translation using Image Information</a></div><div class="wp-workCard_item"><span>Journal of KIISE</span><span>, 2019</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="72e95c65df0c1f13357443a6a848ec4c" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":88368182,"asset_id":82772001,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/88368182/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="82772001"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="82772001"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 82772001; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=82772001]").text(description); $(".js-view-count[data-work-id=82772001]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 82772001; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='82772001']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 82772001, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "72e95c65df0c1f13357443a6a848ec4c" } } $('.js-work-strip[data-work-id=82772001]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":82772001,"title":"English-to-Korean Machine Translation using Image Information","translated_title":"","metadata":{"publisher":"Korean Institute of Information Scientists and Engineers","publication_date":{"day":null,"month":null,"year":2019,"errors":{}},"publication_name":"Journal of KIISE"},"translated_abstract":null,"internal_url":"https://www.academia.edu/82772001/English_to_Korean_Machine_Translation_using_Image_Information","translated_internal_url":"","created_at":"2022-07-07T21:34:05.277-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":88368182,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368182/thumbnails/1.jpg","file_name":"12.pdf","download_url":"https://www.academia.edu/attachments/88368182/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"English_to_Korean_Machine_Translation_us.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368182/12-libre.pdf?1657338107=\u0026response-content-disposition=attachment%3B+filename%3DEnglish_to_Korean_Machine_Translation_us.pdf\u0026Expires=1733028036\u0026Signature=UORXcJfbuTEGrxq5naiCmfknuNoEExZOjcGZRhPO~siIC6sS2I3wS290XcYWkE1Z59aszjPk0opux6BfhQgIeP~FYvtWCIAhPhrJUlCUwu2vktaajKU~jWyg7tCJwlQ4XoVVHaYIdUqFqty9KrUuTTTJGl71To6e3W7jeZGm9OjMbqiFHr0XTa1IP7mr87dwLTldn5LIYwqd9cNXccrK6x4kLzTsxwoJwxvdI1R-gAIJzZtE62pDeiZnKl-4kYErjbefLOZAQIbxuhz8DWDJ4VNbKIFrJCTUN8lo6c4-cLRbiRzv7JN5vWkTCUvsYE8ewNXEZNWqQE7F5SDpA3U4AQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"English_to_Korean_Machine_Translation_using_Image_Information","translated_slug":"","page_count":7,"language":"ko","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":88368182,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368182/thumbnails/1.jpg","file_name":"12.pdf","download_url":"https://www.academia.edu/attachments/88368182/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNiw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"English_to_Korean_Machine_Translation_us.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368182/12-libre.pdf?1657338107=\u0026response-content-disposition=attachment%3B+filename%3DEnglish_to_Korean_Machine_Translation_us.pdf\u0026Expires=1733028036\u0026Signature=UORXcJfbuTEGrxq5naiCmfknuNoEExZOjcGZRhPO~siIC6sS2I3wS290XcYWkE1Z59aszjPk0opux6BfhQgIeP~FYvtWCIAhPhrJUlCUwu2vktaajKU~jWyg7tCJwlQ4XoVVHaYIdUqFqty9KrUuTTTJGl71To6e3W7jeZGm9OjMbqiFHr0XTa1IP7mr87dwLTldn5LIYwqd9cNXccrK6x4kLzTsxwoJwxvdI1R-gAIJzZtE62pDeiZnKl-4kYErjbefLOZAQIbxuhz8DWDJ4VNbKIFrJCTUN8lo6c4-cLRbiRzv7JN5vWkTCUvsYE8ewNXEZNWqQE7F5SDpA3U4AQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="82771977"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/82771977/End_to_end_Korean_Document_Summarization_using_Copy_Mechanism_and_Input_feeding"><img alt="Research paper thumbnail of End-to-end Korean Document Summarization using Copy Mechanism and Input-feeding" class="work-thumbnail" src="https://attachments.academia-assets.com/88368176/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/82771977/End_to_end_Korean_Document_Summarization_using_Copy_Mechanism_and_Input_feeding">End-to-end Korean Document Summarization using Copy Mechanism and Input-feeding</a></div><div class="wp-workCard_item"><span>Journal of KIISE</span><span>, 2017</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="21b1dd1cf71c2f9a17e85b62ff8c6993" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":88368176,"asset_id":82771977,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/88368176/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="82771977"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="82771977"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 82771977; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=82771977]").text(description); $(".js-view-count[data-work-id=82771977]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 82771977; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='82771977']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 82771977, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "21b1dd1cf71c2f9a17e85b62ff8c6993" } } $('.js-work-strip[data-work-id=82771977]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":82771977,"title":"End-to-end Korean Document Summarization using Copy Mechanism and Input-feeding","translated_title":"","metadata":{"publisher":"Korean Institute of Information Scientists and Engineers","grobid_abstract":"In this paper, the copy mechanism and input feeding are applied to recurrent neural network(RNN)-search model in a Korean-document summarization in an end-to-end manner. In addition, the performances of the document summarizations are compared according to the model and the tokenization format; accordingly, the syllable-unit, morpheme-unit, and hybrid-unit tokenization formats are compared. For the experiments, Internet newspaper articles were collected to construct a Korean-document summary data set (train set: 30291 documents; development set: 3786 documents; test set: 3705 documents). When the format was tokenized as the morpheme-unit, the models with the input feeding and the copy mechanism showed the highest performances of ROUGE-1 35.92, ROUGE-2 15.37, and ROUGE-L 29.45.","publication_date":{"day":null,"month":null,"year":2017,"errors":{}},"publication_name":"Journal of KIISE","grobid_abstract_attachment_id":88368176},"translated_abstract":null,"internal_url":"https://www.academia.edu/82771977/End_to_end_Korean_Document_Summarization_using_Copy_Mechanism_and_Input_feeding","translated_internal_url":"","created_at":"2022-07-07T21:33:31.619-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":88368176,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368176/thumbnails/1.jpg","file_name":"08.pdf","download_url":"https://www.academia.edu/attachments/88368176/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"End_to_end_Korean_Document_Summarization.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368176/08-libre.pdf?1657338112=\u0026response-content-disposition=attachment%3B+filename%3DEnd_to_end_Korean_Document_Summarization.pdf\u0026Expires=1733028036\u0026Signature=bwnByb0ZBLg0QQ6v9mcbk3jt74qBwPvxS3ek4wTrvcweNeJ3zVX4FMs5VWdquf8QSy~Yt~LHf-PslCBtM4jGkg5LxMQlM~evZIXnJiXUaCCED2HMqZo2UANFN2z1k24QdWmLNGYNVfn19IUvvejyuy7Aa3TMv2qKuJOmgIJ0OoEimTIGUXqrQglYzKbH-MnIAMHS1Sg0nQzbLdaA9Hvxom3YLcDgS0bR5PIFAqR9X~txkbd0xb9h2bhSfE-XqD1uf8XJmKSroFiEqotffq5h-FaLXvuoG3YKWFjf6lVrJJxiGaXxU6cUGb8fa44KPTXmKqMqGL-lfC0rzHTcPOs-cw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"End_to_end_Korean_Document_Summarization_using_Copy_Mechanism_and_Input_feeding","translated_slug":"","page_count":7,"language":"ko","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":88368176,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368176/thumbnails/1.jpg","file_name":"08.pdf","download_url":"https://www.academia.edu/attachments/88368176/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"End_to_end_Korean_Document_Summarization.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368176/08-libre.pdf?1657338112=\u0026response-content-disposition=attachment%3B+filename%3DEnd_to_end_Korean_Document_Summarization.pdf\u0026Expires=1733028036\u0026Signature=bwnByb0ZBLg0QQ6v9mcbk3jt74qBwPvxS3ek4wTrvcweNeJ3zVX4FMs5VWdquf8QSy~Yt~LHf-PslCBtM4jGkg5LxMQlM~evZIXnJiXUaCCED2HMqZo2UANFN2z1k24QdWmLNGYNVfn19IUvvejyuy7Aa3TMv2qKuJOmgIJ0OoEimTIGUXqrQglYzKbH-MnIAMHS1Sg0nQzbLdaA9Hvxom3YLcDgS0bR5PIFAqR9X~txkbd0xb9h2bhSfE-XqD1uf8XJmKSroFiEqotffq5h-FaLXvuoG3YKWFjf6lVrJJxiGaXxU6cUGb8fa44KPTXmKqMqGL-lfC0rzHTcPOs-cw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="82771953"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/82771953/SiteQ_Engineering_high_performance_QA_system_using_lexico_semantic_pattern_matching_and_shallow_NLP"><img alt="Research paper thumbnail of SiteQ: Engineering high performance QA system using lexico-semantic pattern matching and shallow NLP" class="work-thumbnail" src="https://attachments.academia-assets.com/88368787/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/82771953/SiteQ_Engineering_high_performance_QA_system_using_lexico_semantic_pattern_matching_and_shallow_NLP">SiteQ: Engineering high performance QA system using lexico-semantic pattern matching and shallow NLP</a></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="9f75a17ec2c17496cdc14b7059d219b9" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":88368787,"asset_id":82771953,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/88368787/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="82771953"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="82771953"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 82771953; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=82771953]").text(description); $(".js-view-count[data-work-id=82771953]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 82771953; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='82771953']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 82771953, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "9f75a17ec2c17496cdc14b7059d219b9" } } $('.js-work-strip[data-work-id=82771953]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":82771953,"title":"SiteQ: Engineering high performance QA system using lexico-semantic pattern matching and shallow NLP","translated_title":"","metadata":{"grobid_abstract":"In TREC-10, we participated in the web track (only ad-hoc task) and the QA track (only main task). In the QA track, our QA system (SiteQ) has general architecture with three processing steps: question processing, passage selection and answer processing. The key technique is LSP's (Lexico-Semantic Patterns) that are composed of linguistic entries and semantic types. LSP grammars constructed from various resources are used for answer type determination and answer matching. We also adapt AAD (Abbreviation-Appositive-Definition) processing for the queries that answer type cannot be determined or expected, encyclopedia search for increasing the matching coverage between query terms and passages, and pivot detection for the distance calculation with answer candidates. We used two-level answer types consisted of 18 upper-level types and 47 lower-level types. Semantic category dictionary, WordNet, POS combined with lexicography and a stemmer were all applied to construct the LSP knowledge base. CSMT (Category Sense-code Mapping Table) tried to find answer types using the matching between semantic categories and sense-codes from WordNet. Evaluation shows that MRR for 492 questions is 0.320 (strict), which is considerably higher than the average MRR of other 67 runs. In the Web track, we focused on the effectiveness of both noun phrase extraction and our new PRF (Pseudo Relevance Feedback). We confirmed that our query expansion using PRF with TSV function adapting TF factor contributed to better performance, but noun phrases did not contribute much. It needs more observations for us to make elaborate rules of tag patterns for the construction of better noun phrases.","publication_date":{"day":null,"month":null,"year":2001,"errors":{}},"grobid_abstract_attachment_id":88368787},"translated_abstract":null,"internal_url":"https://www.academia.edu/82771953/SiteQ_Engineering_high_performance_QA_system_using_lexico_semantic_pattern_matching_and_shallow_NLP","translated_internal_url":"","created_at":"2022-07-07T21:32:55.566-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":88368787,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368787/thumbnails/1.jpg","file_name":"siteq_trec10.pdf","download_url":"https://www.academia.edu/attachments/88368787/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"SiteQ_Engineering_high_performance_QA_sy.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368787/siteq_trec10-libre.pdf?1657338761=\u0026response-content-disposition=attachment%3B+filename%3DSiteQ_Engineering_high_performance_QA_sy.pdf\u0026Expires=1733028037\u0026Signature=ZLIrmFoTV1~-sI5up7K55i0o2j1XJtYcx3FQsm4Hnu2ow7JkV5xwlScu4WDlOWer9z-qFxJK9szYUQTVYG-P8rJ-dFJTlzpXiVZbrV13pR4vXqX2BAuop9iRrW2XchK2TkYZ0UclH8ESn11OcVHSvJpshSLIRNDkPxrSy5r-NuWMjV-P3rbZKI76DK7hPQzFr9IGFy~S-rhiYJ9tRC1kqtJTj0I12TJ-NSTmfZHGTHliw4s9QF8tFClwUnLoE9tEKiz4yJXRh4x5gCjdrKhbP2CL1z2uRV294jgRJmoVKloP3vK-k6Tr7TlffSRBU-Zsugbmvn--EJ0MifnBlDsvZw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"SiteQ_Engineering_high_performance_QA_system_using_lexico_semantic_pattern_matching_and_shallow_NLP","translated_slug":"","page_count":10,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":88368787,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368787/thumbnails/1.jpg","file_name":"siteq_trec10.pdf","download_url":"https://www.academia.edu/attachments/88368787/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"SiteQ_Engineering_high_performance_QA_sy.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368787/siteq_trec10-libre.pdf?1657338761=\u0026response-content-disposition=attachment%3B+filename%3DSiteQ_Engineering_high_performance_QA_sy.pdf\u0026Expires=1733028037\u0026Signature=ZLIrmFoTV1~-sI5up7K55i0o2j1XJtYcx3FQsm4Hnu2ow7JkV5xwlScu4WDlOWer9z-qFxJK9szYUQTVYG-P8rJ-dFJTlzpXiVZbrV13pR4vXqX2BAuop9iRrW2XchK2TkYZ0UclH8ESn11OcVHSvJpshSLIRNDkPxrSy5r-NuWMjV-P3rbZKI76DK7hPQzFr9IGFy~S-rhiYJ9tRC1kqtJTj0I12TJ-NSTmfZHGTHliw4s9QF8tFClwUnLoE9tEKiz4yJXRh4x5gCjdrKhbP2CL1z2uRV294jgRJmoVKloP3vK-k6Tr7TlffSRBU-Zsugbmvn--EJ0MifnBlDsvZw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":422,"name":"Computer Science","url":"https://www.academia.edu/Documents/in/Computer_Science"},{"id":465,"name":"Artificial Intelligence","url":"https://www.academia.edu/Documents/in/Artificial_Intelligence"},{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":143286,"name":"Noun Phrase","url":"https://www.academia.edu/Documents/in/Noun_Phrase"},{"id":155958,"name":"Pattern Matching","url":"https://www.academia.edu/Documents/in/Pattern_Matching"},{"id":212580,"name":"Query Expansion","url":"https://www.academia.edu/Documents/in/Query_Expansion"},{"id":246163,"name":"Knowledge base","url":"https://www.academia.edu/Documents/in/Knowledge_base"},{"id":274507,"name":"TREC","url":"https://www.academia.edu/Documents/in/TREC"},{"id":297691,"name":"High performance","url":"https://www.academia.edu/Documents/in/High_performance"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="82771763"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/82771763/Korean_Semantic_Role_Labeling_with_Bidirectional_Encoder_Representations_from_Transformers_and_Simple_Semantic_Information"><img alt="Research paper thumbnail of Korean Semantic Role Labeling with Bidirectional Encoder Representations from Transformers and Simple Semantic Information" class="work-thumbnail" src="https://attachments.academia-assets.com/88368087/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/82771763/Korean_Semantic_Role_Labeling_with_Bidirectional_Encoder_Representations_from_Transformers_and_Simple_Semantic_Information">Korean Semantic Role Labeling with Bidirectional Encoder Representations from Transformers and Simple Semantic Information</a></div><div class="wp-workCard_item"><span>Applied Sciences</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">State-of-the-art semantic role labeling (SRL) performance has been achieved using neural network ...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">State-of-the-art semantic role labeling (SRL) performance has been achieved using neural network models by incorporating syntactic feature information such as dependency trees. In recent years, breakthroughs achieved using end-to-end neural network models have resulted in a state-of-the-art SRL performance even without syntactic features. With the advent of a language model called bidirectional encoder representations from transformers (BERT), another breakthrough was witnessed. Even though the semantic information of each word constituting a sentence is important in determining the meaning of a word, previous studies regarding the end-to-end neural network method did not utilize semantic information. In this study, we propose a BERT-based SRL model that uses simple semantic information without syntactic feature information. To obtain the latter, we used PropBank, which described the relational information between predicates and arguments. In addition, text-originated feature inform...</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="454597bb8348c8b50e16bae5f6eddabf" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":88368087,"asset_id":82771763,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/88368087/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="82771763"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="82771763"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 82771763; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=82771763]").text(description); $(".js-view-count[data-work-id=82771763]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 82771763; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='82771763']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 82771763, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "454597bb8348c8b50e16bae5f6eddabf" } } $('.js-work-strip[data-work-id=82771763]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":82771763,"title":"Korean Semantic Role Labeling with Bidirectional Encoder Representations from Transformers and Simple Semantic Information","translated_title":"","metadata":{"abstract":"State-of-the-art semantic role labeling (SRL) performance has been achieved using neural network models by incorporating syntactic feature information such as dependency trees. In recent years, breakthroughs achieved using end-to-end neural network models have resulted in a state-of-the-art SRL performance even without syntactic features. With the advent of a language model called bidirectional encoder representations from transformers (BERT), another breakthrough was witnessed. Even though the semantic information of each word constituting a sentence is important in determining the meaning of a word, previous studies regarding the end-to-end neural network method did not utilize semantic information. In this study, we propose a BERT-based SRL model that uses simple semantic information without syntactic feature information. To obtain the latter, we used PropBank, which described the relational information between predicates and arguments. In addition, text-originated feature inform...","publisher":"MDPI AG","publication_name":"Applied Sciences"},"translated_abstract":"State-of-the-art semantic role labeling (SRL) performance has been achieved using neural network models by incorporating syntactic feature information such as dependency trees. In recent years, breakthroughs achieved using end-to-end neural network models have resulted in a state-of-the-art SRL performance even without syntactic features. With the advent of a language model called bidirectional encoder representations from transformers (BERT), another breakthrough was witnessed. Even though the semantic information of each word constituting a sentence is important in determining the meaning of a word, previous studies regarding the end-to-end neural network method did not utilize semantic information. In this study, we propose a BERT-based SRL model that uses simple semantic information without syntactic feature information. To obtain the latter, we used PropBank, which described the relational information between predicates and arguments. In addition, text-originated feature inform...","internal_url":"https://www.academia.edu/82771763/Korean_Semantic_Role_Labeling_with_Bidirectional_Encoder_Representations_from_Transformers_and_Simple_Semantic_Information","translated_internal_url":"","created_at":"2022-07-07T21:30:32.988-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":88368087,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368087/thumbnails/1.jpg","file_name":"pdf.pdf","download_url":"https://www.academia.edu/attachments/88368087/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Korean_Semantic_Role_Labeling_with_Bidir.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368087/pdf-libre.pdf?1657337829=\u0026response-content-disposition=attachment%3B+filename%3DKorean_Semantic_Role_Labeling_with_Bidir.pdf\u0026Expires=1733028037\u0026Signature=M7JZuIgWlyENOnR-wwIKwPvqZSkiHGdQQ5sHSdypPszorJY8qbShT6Wex4tEgTC~KNFDwTQlr4E5HDHtIvcUNw~lMHcMGwKNQhviAUI4QJ~f3G1y4k3fLfHXxwH2L7kJeEWRqrQMMWwXY21fwLBf~7tR6TGgsc7kILHwx5ipTrADUIOWeJ9iVv2RG0fECzlLsDjZc9Sz0csZHFdd8H~9PKFH9OpC9KD~6NG24nJKHgGv~0DSKN4OMh~Lctu1mP1itJ8LbiDb~dF~PyJ5vFXR-~hs20OEqSIC3dZ0IaBzJ9kOa7KiYLWZ28crM0lzCZNDwy6jEHStat3KYc6ZA8ZZaQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Korean_Semantic_Role_Labeling_with_Bidirectional_Encoder_Representations_from_Transformers_and_Simple_Semantic_Information","translated_slug":"","page_count":9,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":88368087,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/88368087/thumbnails/1.jpg","file_name":"pdf.pdf","download_url":"https://www.academia.edu/attachments/88368087/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Korean_Semantic_Role_Labeling_with_Bidir.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/88368087/pdf-libre.pdf?1657337829=\u0026response-content-disposition=attachment%3B+filename%3DKorean_Semantic_Role_Labeling_with_Bidir.pdf\u0026Expires=1733028037\u0026Signature=M7JZuIgWlyENOnR-wwIKwPvqZSkiHGdQQ5sHSdypPszorJY8qbShT6Wex4tEgTC~KNFDwTQlr4E5HDHtIvcUNw~lMHcMGwKNQhviAUI4QJ~f3G1y4k3fLfHXxwH2L7kJeEWRqrQMMWwXY21fwLBf~7tR6TGgsc7kILHwx5ipTrADUIOWeJ9iVv2RG0fECzlLsDjZc9Sz0csZHFdd8H~9PKFH9OpC9KD~6NG24nJKHgGv~0DSKN4OMh~Lctu1mP1itJ8LbiDb~dF~PyJ5vFXR-~hs20OEqSIC3dZ0IaBzJ9kOa7KiYLWZ28crM0lzCZNDwy6jEHStat3KYc6ZA8ZZaQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":159232,"name":"Applied Sciences","url":"https://www.academia.edu/Documents/in/Applied_Sciences"}],"urls":[{"id":21998260,"url":"https://www.mdpi.com/2076-3417/12/12/5995/pdf"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="72121117"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" href="https://www.academia.edu/72121117/Systematic_Construction_of_Hierarchical_Classifier_in_SVM_Based_Text_Categorization"><img alt="Research paper thumbnail of Systematic Construction of Hierarchical Classifier in SVM-Based Text Categorization" class="work-thumbnail" src="https://attachments.academia-assets.com/81178132/thumbnails/1.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" href="https://www.academia.edu/72121117/Systematic_Construction_of_Hierarchical_Classifier_in_SVM_Based_Text_Categorization">Systematic Construction of Hierarchical Classifier in SVM-Based Text Categorization</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Abstract. In a text categorization task, classification on some hierar-chy of classes shows bette...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">Abstract. In a text categorization task, classification on some hierar-chy of classes shows better results than the case without the hierarchy. In current environments where large amount of documents are divided into several subgroups with a hierarchy between them, it is more natural and appropriate to use a hierarchical classification method. We intro-duce a new internal node evaluation scheme which is very helpful to the development process of a hierarchical classifier. We also show that the hierarchical classifier construction method using this measure yields a classifier with better classification performance especially when applied to the classification task with large depth of hierarchy. 1</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="1ca7741dbc512e9865436db12e0f08df" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":81178132,"asset_id":72121117,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/81178132/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&s=profile"><span><i class="fa fa-arrow-down"></i></span><span>Download</span></a><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="72121117"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="72121117"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 72121117; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=72121117]").text(description); $(".js-view-count[data-work-id=72121117]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 72121117; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='72121117']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 72121117, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (true){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "1ca7741dbc512e9865436db12e0f08df" } } $('.js-work-strip[data-work-id=72121117]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":72121117,"title":"Systematic Construction of Hierarchical Classifier in SVM-Based Text Categorization","translated_title":"","metadata":{"abstract":"Abstract. In a text categorization task, classification on some hierar-chy of classes shows better results than the case without the hierarchy. In current environments where large amount of documents are divided into several subgroups with a hierarchy between them, it is more natural and appropriate to use a hierarchical classification method. We intro-duce a new internal node evaluation scheme which is very helpful to the development process of a hierarchical classifier. We also show that the hierarchical classifier construction method using this measure yields a classifier with better classification performance especially when applied to the classification task with large depth of hierarchy. 1","publication_date":{"day":null,"month":null,"year":2004,"errors":{}}},"translated_abstract":"Abstract. In a text categorization task, classification on some hierar-chy of classes shows better results than the case without the hierarchy. In current environments where large amount of documents are divided into several subgroups with a hierarchy between them, it is more natural and appropriate to use a hierarchical classification method. We intro-duce a new internal node evaluation scheme which is very helpful to the development process of a hierarchical classifier. We also show that the hierarchical classifier construction method using this measure yields a classifier with better classification performance especially when applied to the classification task with large depth of hierarchy. 1","internal_url":"https://www.academia.edu/72121117/Systematic_Construction_of_Hierarchical_Classifier_in_SVM_Based_Text_Categorization","translated_internal_url":"","created_at":"2022-02-21T10:32:13.980-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[{"id":81178132,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/81178132/thumbnails/1.jpg","file_name":"hierc_ijcnlp.pdf","download_url":"https://www.academia.edu/attachments/81178132/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Systematic_Construction_of_Hierarchical.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/81178132/hierc_ijcnlp-libre.pdf?1645469013=\u0026response-content-disposition=attachment%3B+filename%3DSystematic_Construction_of_Hierarchical.pdf\u0026Expires=1733028037\u0026Signature=ZWxc9Z9SI~PsKkO~kegBJU9jItffjeQkGfRJR1skG3C84Gz-s~ihOCs8ytGujePUB7i7enFTb2ZLchCybM~K~EyWq7BWgGMhHKRc5h3MDCt5J5ddTa5FhsviiGmM4GgZVnJoz5e~uMWBvCVLtDTXWPmvoqBFYjX-X-Ufbkr5vSPCEejW2LGI3QCA3dI-QwHWlv5hVmUekIU4~bIvkcnqbpcVo2K83yKpiIlSXnDIoCzeZ9z9jPnPlexqcn2apj6r0NWzX1CkSmMJpkDGe2Hv-TBFB4k3wNxZavQPpSzjeAvuDyxUrN7g18Pb5RpjHq~MCwU4dBehaWO8an9Z5EhyRA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Systematic_Construction_of_Hierarchical_Classifier_in_SVM_Based_Text_Categorization","translated_slug":"","page_count":8,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[{"id":81178132,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/81178132/thumbnails/1.jpg","file_name":"hierc_ijcnlp.pdf","download_url":"https://www.academia.edu/attachments/81178132/download_file?st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&st=MTczMzAyNDQzNyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Systematic_Construction_of_Hierarchical.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/81178132/hierc_ijcnlp-libre.pdf?1645469013=\u0026response-content-disposition=attachment%3B+filename%3DSystematic_Construction_of_Hierarchical.pdf\u0026Expires=1733028037\u0026Signature=ZWxc9Z9SI~PsKkO~kegBJU9jItffjeQkGfRJR1skG3C84Gz-s~ihOCs8ytGujePUB7i7enFTb2ZLchCybM~K~EyWq7BWgGMhHKRc5h3MDCt5J5ddTa5FhsviiGmM4GgZVnJoz5e~uMWBvCVLtDTXWPmvoqBFYjX-X-Ufbkr5vSPCEejW2LGI3QCA3dI-QwHWlv5hVmUekIU4~bIvkcnqbpcVo2K83yKpiIlSXnDIoCzeZ9z9jPnPlexqcn2apj6r0NWzX1CkSmMJpkDGe2Hv-TBFB4k3wNxZavQPpSzjeAvuDyxUrN7g18Pb5RpjHq~MCwU4dBehaWO8an9Z5EhyRA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":582043,"name":"Development Process","url":"https://www.academia.edu/Documents/in/Development_Process"}],"urls":[{"id":17904128,"url":"http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.535.6381\u0026rep=rep1\u0026type=pdf"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="72121116"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/72121116/Automatic_WordNet_mapping_using_word_sense_disambiguation"><img alt="Research paper thumbnail of Automatic WordNet mapping using word sense disambiguation" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/72121116/Automatic_WordNet_mapping_using_word_sense_disambiguation">Automatic WordNet mapping using word sense disambiguation</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">This paper presents the automatic construction of a Korean WordNet from pre-existing lexical reso...</span><a class="js-work-more-abstract" data-broccoli-component="work_strip.more_abstract" data-click-track="profile-work-strip-more-abstract" href="javascript:;"><span> more </span><span><i class="fa fa-caret-down"></i></span></a><span class="js-work-more-abstract-untruncated hidden">This paper presents the automatic construction of a Korean WordNet from pre-existing lexical resources. A set of automatic WSD techniques is described for linking Korean words collected from a bilingual MRD to English WordNet synsets.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="72121116"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="72121116"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 72121116; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=72121116]").text(description); $(".js-view-count[data-work-id=72121116]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 72121116; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='72121116']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 72121116, container: "", }); });</script></span></div><div id="work-strip-premium-row-container"></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/work_edit-ad038b8c047c1a8d4fa01b402d530ff93c45fee2137a149a4a5398bc8ad67560.js"], function() { // from javascript_helper.rb var dispatcherData = {} if (false){ window.WowProfile.dispatcher = window.WowProfile.dispatcher || _.clone(Backbone.Events); dispatcherData = { dispatcher: window.WowProfile.dispatcher, downloadLinkId: "-1" } } $('.js-work-strip[data-work-id=72121116]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":72121116,"title":"Automatic WordNet mapping using word sense disambiguation","translated_title":"","metadata":{"abstract":"This paper presents the automatic construction of a Korean WordNet from pre-existing lexical resources. A set of automatic WSD techniques is described for linking Korean words collected from a bilingual MRD to English WordNet synsets.","publication_date":{"day":null,"month":null,"year":2000,"errors":{}}},"translated_abstract":"This paper presents the automatic construction of a Korean WordNet from pre-existing lexical resources. A set of automatic WSD techniques is described for linking Korean words collected from a bilingual MRD to English WordNet synsets.","internal_url":"https://www.academia.edu/72121116/Automatic_WordNet_mapping_using_word_sense_disambiguation","translated_internal_url":"","created_at":"2022-02-21T10:32:13.826-08:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":34012167,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[],"downloadable_attachments":[],"slug":"Automatic_WordNet_mapping_using_word_sense_disambiguation","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":34012167,"first_name":"Changki","middle_initials":null,"last_name":"Lee","page_name":"ChangkiLee","domain_name":"kangwon","created_at":"2015-08-18T07:20:28.132-07:00","display_name":"Changki Lee","url":"https://kangwon.academia.edu/ChangkiLee"},"attachments":[],"research_interests":[],"urls":[{"id":17904127,"url":"http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.12.8959\u0026rep=rep1\u0026type=pdf"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> </div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js","https://a.academia-assets.com/assets/google_contacts-0dfb882d836b94dbcb4a2d123d6933fc9533eda5be911641f20b4eb428429600.js"], function() { // from javascript_helper.rb $('.js-google-connect-button').click(function(e) { e.preventDefault(); GoogleContacts.authorize_and_show_contacts(); Aedu.Dismissibles.recordClickthrough("WowProfileImportContactsPrompt"); }); $('.js-update-biography-button').click(function(e) { e.preventDefault(); Aedu.Dismissibles.recordClickthrough("UpdateUserBiographyPrompt"); $.ajax({ url: $r.api_v0_profiles_update_about_path({ subdomain_param: 'api', about: "", }), type: 'PUT', success: function(response) { location.reload(); } }); }); $('.js-work-creator-button').click(function (e) { e.preventDefault(); window.location = $r.upload_funnel_document_path({ source: encodeURIComponent(""), }); }); $('.js-video-upload-button').click(function (e) { e.preventDefault(); window.location = $r.upload_funnel_video_path({ source: encodeURIComponent(""), }); }); $('.js-do-this-later-button').click(function() { $(this).closest('.js-profile-nag-panel').remove(); Aedu.Dismissibles.recordDismissal("WowProfileImportContactsPrompt"); }); $('.js-update-biography-do-this-later-button').click(function(){ $(this).closest('.js-profile-nag-panel').remove(); Aedu.Dismissibles.recordDismissal("UpdateUserBiographyPrompt"); }); $('.wow-profile-mentions-upsell--close').click(function(){ $('.wow-profile-mentions-upsell--panel').hide(); Aedu.Dismissibles.recordDismissal("WowProfileMentionsUpsell"); }); $('.wow-profile-mentions-upsell--button').click(function(){ Aedu.Dismissibles.recordClickthrough("WowProfileMentionsUpsell"); }); new WowProfile.SocialRedesignUserWorks({ initialWorksOffset: 20, allWorksOffset: 20, maxSections: 1 }) }); </script> </div></div></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/wow_profile_edit-5ea339ee107c863779f560dd7275595239fed73f1a13d279d2b599a28c0ecd33.js","https://a.academia-assets.com/assets/add_coauthor-22174b608f9cb871d03443cafa7feac496fb50d7df2d66a53f5ee3c04ba67f53.js","https://a.academia-assets.com/assets/tab-dcac0130902f0cc2d8cb403714dd47454f11fc6fb0e99ae6a0827b06613abc20.js","https://a.academia-assets.com/assets/wow_profile-f77ea15d77ce96025a6048a514272ad8becbad23c641fc2b3bd6e24ca6ff1932.js"], function() { // from javascript_helper.rb window.ae = window.ae || {}; window.ae.WowProfile = window.ae.WowProfile || {}; if(Aedu.User.current && Aedu.User.current.id === $viewedUser.id) { window.ae.WowProfile.current_user_edit = {}; new WowProfileEdit.EditUploadView({ el: '.js-edit-upload-button-wrapper', model: window.$current_user, }); new AddCoauthor.AddCoauthorsController(); } var userInfoView = new WowProfile.SocialRedesignUserInfo({ recaptcha_key: "6LdxlRMTAAAAADnu_zyLhLg0YF9uACwz78shpjJB" }); WowProfile.router = new WowProfile.Router({ userInfoView: userInfoView }); Backbone.history.start({ pushState: true, root: "/" + $viewedUser.page_name }); new WowProfile.UserWorksNav() }); </script> </div> <div class="bootstrap login"><div class="modal fade login-modal" id="login-modal"><div class="login-modal-dialog modal-dialog"><div class="modal-content"><div class="modal-header"><button class="close close" data-dismiss="modal" type="button"><span aria-hidden="true">×</span><span class="sr-only">Close</span></button><h4 class="modal-title text-center"><strong>Log In</strong></h4></div><div class="modal-body"><div class="row"><div class="col-xs-10 col-xs-offset-1"><button class="btn btn-fb btn-lg btn-block btn-v-center-content" id="login-facebook-oauth-button"><svg style="float: left; width: 19px; line-height: 1em; margin-right: .3em;" aria-hidden="true" focusable="false" data-prefix="fab" data-icon="facebook-square" class="svg-inline--fa fa-facebook-square fa-w-14" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><path fill="currentColor" d="M400 32H48A48 48 0 0 0 0 80v352a48 48 0 0 0 48 48h137.25V327.69h-63V256h63v-54.64c0-62.15 37-96.48 93.67-96.48 27.14 0 55.52 4.84 55.52 4.84v61h-31.27c-30.81 0-40.42 19.12-40.42 38.73V256h68.78l-11 71.69h-57.78V480H400a48 48 0 0 0 48-48V80a48 48 0 0 0-48-48z"></path></svg><small><strong>Log in</strong> with <strong>Facebook</strong></small></button><br /><button class="btn btn-google btn-lg btn-block btn-v-center-content" id="login-google-oauth-button"><svg style="float: left; width: 22px; line-height: 1em; margin-right: .3em;" aria-hidden="true" focusable="false" data-prefix="fab" data-icon="google-plus" class="svg-inline--fa fa-google-plus fa-w-16" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path fill="currentColor" d="M256,8C119.1,8,8,119.1,8,256S119.1,504,256,504,504,392.9,504,256,392.9,8,256,8ZM185.3,380a124,124,0,0,1,0-248c31.3,0,60.1,11,83,32.3l-33.6,32.6c-13.2-12.9-31.3-19.1-49.4-19.1-42.9,0-77.2,35.5-77.2,78.1S142.3,334,185.3,334c32.6,0,64.9-19.1,70.1-53.3H185.3V238.1H302.2a109.2,109.2,0,0,1,1.9,20.7c0,70.8-47.5,121.2-118.8,121.2ZM415.5,273.8v35.5H380V273.8H344.5V238.3H380V202.8h35.5v35.5h35.2v35.5Z"></path></svg><small><strong>Log in</strong> with <strong>Google</strong></small></button><br /><style type="text/css">.sign-in-with-apple-button { width: 100%; height: 52px; border-radius: 3px; border: 1px solid black; cursor: pointer; }</style><script src="https://appleid.cdn-apple.com/appleauth/static/jsapi/appleid/1/en_US/appleid.auth.js" type="text/javascript"></script><div class="sign-in-with-apple-button" data-border="false" data-color="white" id="appleid-signin"><span   ="Sign Up with Apple" class="u-fs11"></span></div><script>AppleID.auth.init({ clientId: 'edu.academia.applesignon', scope: 'name email', redirectURI: 'https://www.academia.edu/sessions', state: "a6ab2aabbedb58dc48a21cdcd5ca56aacddeee5449886f5ec2bde470943fc16d", });</script><script>// Hacky way of checking if on fast loswp if (window.loswp == null) { (function() { const Google = window?.Aedu?.Auth?.OauthButton?.Login?.Google; const Facebook = window?.Aedu?.Auth?.OauthButton?.Login?.Facebook; if (Google) { new Google({ el: '#login-google-oauth-button', rememberMeCheckboxId: 'remember_me', track: null }); } if (Facebook) { new Facebook({ el: '#login-facebook-oauth-button', rememberMeCheckboxId: 'remember_me', track: null }); } })(); }</script></div></div></div><div class="modal-body"><div class="row"><div class="col-xs-10 col-xs-offset-1"><div class="hr-heading login-hr-heading"><span class="hr-heading-text">or</span></div></div></div></div><div class="modal-body"><div class="row"><div class="col-xs-10 col-xs-offset-1"><form class="js-login-form" action="https://www.academia.edu/sessions" accept-charset="UTF-8" method="post"><input name="utf8" type="hidden" value="✓" autocomplete="off" /><input type="hidden" name="authenticity_token" value="ZOceeA+7gMxEK9wCycLoR4PpN3jPvzrKKnHamaNYonOJIsZp7pg2ifFN/pO6DZ63Bi92EmycRcaZ/4RDmHLbww==" autocomplete="off" /><div class="form-group"><label class="control-label" for="login-modal-email-input" style="font-size: 14px;">Email</label><input class="form-control" id="login-modal-email-input" name="login" type="email" /></div><div class="form-group"><label class="control-label" for="login-modal-password-input" style="font-size: 14px;">Password</label><input class="form-control" id="login-modal-password-input" name="password" type="password" /></div><input type="hidden" name="post_login_redirect_url" id="post_login_redirect_url" value="https://kangwon.academia.edu/ChangkiLee" autocomplete="off" /><div class="checkbox"><label><input type="checkbox" name="remember_me" id="remember_me" value="1" checked="checked" /><small style="font-size: 12px; margin-top: 2px; display: inline-block;">Remember me on this computer</small></label></div><br><input type="submit" name="commit" value="Log In" class="btn btn-primary btn-block btn-lg js-login-submit" data-disable-with="Log In" /></br></form><script>typeof window?.Aedu?.recaptchaManagedForm === 'function' && window.Aedu.recaptchaManagedForm( document.querySelector('.js-login-form'), document.querySelector('.js-login-submit') );</script><small style="font-size: 12px;"><br />or <a data-target="#login-modal-reset-password-container" data-toggle="collapse" href="javascript:void(0)">reset password</a></small><div class="collapse" id="login-modal-reset-password-container"><br /><div class="well margin-0x"><form class="js-password-reset-form" action="https://www.academia.edu/reset_password" accept-charset="UTF-8" method="post"><input name="utf8" type="hidden" value="✓" autocomplete="off" /><input type="hidden" name="authenticity_token" value="dvEaV5AqhpQVaRxRrd5aJYa9+1pFSzimbOlRQ/bUbHmbNMJGcQkw0aAPPsDeESzVA3u6MOZoR6rfZw+Zzf4VyQ==" autocomplete="off" /><p>Enter the email address you signed up with and we'll email you a reset link.</p><div class="form-group"><input class="form-control" name="email" type="email" /></div><script src="https://recaptcha.net/recaptcha/api.js" async defer></script> <script> var invisibleRecaptchaSubmit = function () { var closestForm = function (ele) { var curEle = ele.parentNode; while (curEle.nodeName !== 'FORM' && curEle.nodeName !== 'BODY'){ curEle = curEle.parentNode; } return curEle.nodeName === 'FORM' ? curEle : null }; var eles = document.getElementsByClassName('g-recaptcha'); if (eles.length > 0) { var form = closestForm(eles[0]); if (form) { form.submit(); } } }; </script> <input type="submit" data-sitekey="6Lf3KHUUAAAAACggoMpmGJdQDtiyrjVlvGJ6BbAj" data-callback="invisibleRecaptchaSubmit" class="g-recaptcha btn btn-primary btn-block" value="Email me a link" value=""/> </form></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/collapse-45805421cf446ca5adf7aaa1935b08a3a8d1d9a6cc5d91a62a2a3a00b20b3e6a.js"], function() { // from javascript_helper.rb $("#login-modal-reset-password-container").on("shown.bs.collapse", function() { $(this).find("input[type=email]").focus(); }); }); </script> </div></div></div><div class="modal-footer"><div class="text-center"><small style="font-size: 12px;">Need an account? <a rel="nofollow" href="https://www.academia.edu/signup">Click here to sign up</a></small></div></div></div></div></div></div><script>// If we are on subdomain or non-bootstrapped page, redirect to login page instead of showing modal (function(){ if (typeof $ === 'undefined') return; var host = window.location.hostname; if ((host === $domain || host === "www."+$domain) && (typeof $().modal === 'function')) { $("#nav_log_in").click(function(e) { // Don't follow the link and open the modal e.preventDefault(); $("#login-modal").on('shown.bs.modal', function() { $(this).find("#login-modal-email-input").focus() }).modal('show'); }); } })()</script> <div class="bootstrap" id="footer"><div class="footer-content clearfix text-center padding-top-7x" style="width:100%;"><ul class="footer-links-secondary footer-links-wide list-inline margin-bottom-1x"><li><a href="https://www.academia.edu/about">About</a></li><li><a href="https://www.academia.edu/press">Press</a></li><li><a rel="nofollow" href="https://medium.com/academia">Blog</a></li><li><a href="https://www.academia.edu/documents">Papers</a></li><li><a href="https://www.academia.edu/topics">Topics</a></li><li><a href="https://www.academia.edu/journals">Academia.edu Journals</a></li><li><a rel="nofollow" href="https://www.academia.edu/hiring"><svg style="width: 13px; height: 13px;" aria-hidden="true" focusable="false" data-prefix="fas" data-icon="briefcase" class="svg-inline--fa fa-briefcase fa-w-16" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path fill="currentColor" d="M320 336c0 8.84-7.16 16-16 16h-96c-8.84 0-16-7.16-16-16v-48H0v144c0 25.6 22.4 48 48 48h416c25.6 0 48-22.4 48-48V288H320v48zm144-208h-80V80c0-25.6-22.4-48-48-48H176c-25.6 0-48 22.4-48 48v48H48c-25.6 0-48 22.4-48 48v80h512v-80c0-25.6-22.4-48-48-48zm-144 0H192V96h128v32z"></path></svg> <strong>We're Hiring!</strong></a></li><li><a rel="nofollow" href="https://support.academia.edu/"><svg style="width: 12px; height: 12px;" aria-hidden="true" focusable="false" data-prefix="fas" data-icon="question-circle" class="svg-inline--fa fa-question-circle fa-w-16" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path fill="currentColor" d="M504 256c0 136.997-111.043 248-248 248S8 392.997 8 256C8 119.083 119.043 8 256 8s248 111.083 248 248zM262.655 90c-54.497 0-89.255 22.957-116.549 63.758-3.536 5.286-2.353 12.415 2.715 16.258l34.699 26.31c5.205 3.947 12.621 3.008 16.665-2.122 17.864-22.658 30.113-35.797 57.303-35.797 20.429 0 45.698 13.148 45.698 32.958 0 14.976-12.363 22.667-32.534 33.976C247.128 238.528 216 254.941 216 296v4c0 6.627 5.373 12 12 12h56c6.627 0 12-5.373 12-12v-1.333c0-28.462 83.186-29.647 83.186-106.667 0-58.002-60.165-102-116.531-102zM256 338c-25.365 0-46 20.635-46 46 0 25.364 20.635 46 46 46s46-20.636 46-46c0-25.365-20.635-46-46-46z"></path></svg> <strong>Help Center</strong></a></li></ul><ul class="footer-links-tertiary list-inline margin-bottom-1x"><li class="small">Find new research papers in:</li><li class="small"><a href="https://www.academia.edu/Documents/in/Physics">Physics</a></li><li class="small"><a href="https://www.academia.edu/Documents/in/Chemistry">Chemistry</a></li><li class="small"><a href="https://www.academia.edu/Documents/in/Biology">Biology</a></li><li class="small"><a href="https://www.academia.edu/Documents/in/Health_Sciences">Health Sciences</a></li><li class="small"><a href="https://www.academia.edu/Documents/in/Ecology">Ecology</a></li><li class="small"><a href="https://www.academia.edu/Documents/in/Earth_Sciences">Earth Sciences</a></li><li class="small"><a href="https://www.academia.edu/Documents/in/Cognitive_Science">Cognitive Science</a></li><li class="small"><a href="https://www.academia.edu/Documents/in/Mathematics">Mathematics</a></li><li class="small"><a href="https://www.academia.edu/Documents/in/Computer_Science">Computer Science</a></li></ul></div></div><div class="DesignSystem" id="credit" style="width:100%;"><ul class="u-pl0x footer-links-legal list-inline"><li><a rel="nofollow" href="https://www.academia.edu/terms">Terms</a></li><li><a rel="nofollow" href="https://www.academia.edu/privacy">Privacy</a></li><li><a rel="nofollow" href="https://www.academia.edu/copyright">Copyright</a></li><li>Academia ©2024</li></ul></div><script> //<![CDATA[ window.detect_gmtoffset = true; window.Academia && window.Academia.set_gmtoffset && Academia.set_gmtoffset('/gmtoffset'); //]]> </script> <div id='overlay_background'></div> <div id='bootstrap-modal-container' class='bootstrap'></div> <div id='ds-modal-container' class='bootstrap DesignSystem'></div> <div id='full-screen-modal'></div> </div> </body> </html>