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>James Henderson - 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="MljQKOYvgKzy0TuN3hMfjNmVCTyhMoS9KB+eRmNINK67fyJjhWUA8OYZUfYdpUxM9oTv6Hlu521fEP8REhnNuA==" /> <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-1c712297ae3ac71207193b1bae0ecf1aae125886850f62c9c0139dd867630797.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="james henderson" /> <meta name="description" content="James Henderson: 13 Followers, 8 Following, 62 Research papers. Research interests: Implicit learning, Language Variation, and Uncertainty." /> <meta name="google-site-verification" content="bKJMBZA7E43xhDOopFZkssMMkBRjvYERV-NaN4R6mrs" /> <script> var $controller_name = 'works'; var $action_name = "summary"; var $rails_env = 'production'; var $app_rev = '49879c2402910372f4abc62630a427bbe033d190'; 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":15276,"monthly_visitors":"112 million","monthly_visitor_count":112794806,"monthly_visitor_count_in_millions":112,"user_count":277184021,"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(1732455147000); window.Aedu.timeDifference = new Date().getTime() - 1732455147000; 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-296162c7af6fd81dcdd76f1a94f1fad04fb5f647401337d136fe8b68742170b1.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-8d53a22151f33ab413d88fa1c02f979c3f8706d470fc1bced09852c72a9f3454.js"></script> <script src="//a.academia-assets.com/assets/webpack_bundles/core_webpack.wjs-bundle-f8fe82512740391f81c9e8cc48220144024b425b359b08194e316f4de070b9e8.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://independent.academia.edu/JamesHenderson28" /> </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-9601d1cc3d68aa07c0a9901d03d3611aec04cc07d2a2039718ebef4ad4d148ca.js" defer="defer"></script><script>Aedu.rankings = { showPaperRankingsLink: false } $viewedUser = Aedu.User.set_viewed( {"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28","photo":"/images/s65_no_pic.png","has_photo":false,"is_analytics_public":false,"interests":[{"id":1753,"name":"Implicit learning","url":"https://www.academia.edu/Documents/in/Implicit_learning"},{"id":30478,"name":"Language Variation","url":"https://www.academia.edu/Documents/in/Language_Variation"},{"id":61603,"name":"Uncertainty","url":"https://www.academia.edu/Documents/in/Uncertainty"},{"id":3268,"name":"Computational Linguistics","url":"https://www.academia.edu/Documents/in/Computational_Linguistics"},{"id":28040,"name":"Music Teacher Education","url":"https://www.academia.edu/Documents/in/Music_Teacher_Education"}]} ); if ($a.is_logged_in() && $viewedUser.is_current_user()) { $('body').addClass('profile-viewed-by-owner'); } $socialProfiles = []</script><div id="js-react-on-rails-context" style="display:none" data-rails-context="{"inMailer":false,"i18nLocale":"en","i18nDefaultLocale":"en","href":"https://independent.academia.edu/JamesHenderson28","location":"/JamesHenderson28","scheme":"https","host":"independent.academia.edu","port":null,"pathname":"/JamesHenderson28","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-0bb277f9-3155-4798-acfe-c9744c29e79d"></div> <div id="ProfileCheckPaperUpdate-react-component-0bb277f9-3155-4798-acfe-c9744c29e79d"></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">James Henderson</h1><div class="affiliations-container fake-truncate js-profile-affiliations"></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="James" data-follow-user-id="33971246" 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="33971246"><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">13</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">8</p></div></a><a><div class="stat-container js-profile-coauthors" data-broccoli-component="user-info.coauthors-count" data-click-track="profile-expand-user-info-coauthors"><p class="label">Co-authors</p><p class="data">6</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="33971246" href="https://www.academia.edu/Documents/in/Implicit_learning"><div id="js-react-on-rails-context" style="display:none" data-rails-context="{"inMailer":false,"i18nLocale":"en","i18nDefaultLocale":"en","href":"https://independent.academia.edu/JamesHenderson28","location":"/JamesHenderson28","scheme":"https","host":"independent.academia.edu","port":null,"pathname":"/JamesHenderson28","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":["Implicit learning"]}" data-trace="false" data-dom-id="Pill-react-component-d13aed89-5eef-4946-8f69-92d5b62594ef"></div> <div id="Pill-react-component-d13aed89-5eef-4946-8f69-92d5b62594ef"></div> </a><a data-click-track="profile-user-info-expand-research-interests" data-has-card-for-ri-list="33971246" href="https://www.academia.edu/Documents/in/Language_Variation"><div class="js-react-on-rails-component" style="display:none" data-component-name="Pill" data-props="{"color":"gray","children":["Language Variation"]}" data-trace="false" data-dom-id="Pill-react-component-9a3021ac-1dec-4792-b135-2ab9d050d23c"></div> <div id="Pill-react-component-9a3021ac-1dec-4792-b135-2ab9d050d23c"></div> </a><a data-click-track="profile-user-info-expand-research-interests" data-has-card-for-ri-list="33971246" href="https://www.academia.edu/Documents/in/Uncertainty"><div class="js-react-on-rails-component" style="display:none" data-component-name="Pill" data-props="{"color":"gray","children":["Uncertainty"]}" data-trace="false" data-dom-id="Pill-react-component-a3abf53b-f83b-4da5-aa71-68965afc0bc5"></div> <div id="Pill-react-component-a3abf53b-f83b-4da5-aa71-68965afc0bc5"></div> </a><a data-click-track="profile-user-info-expand-research-interests" data-has-card-for-ri-list="33971246" href="https://www.academia.edu/Documents/in/Computational_Linguistics"><div class="js-react-on-rails-component" style="display:none" data-component-name="Pill" data-props="{"color":"gray","children":["Computational Linguistics"]}" data-trace="false" data-dom-id="Pill-react-component-a33f58b8-5572-4fbf-8f8b-18bc1f173928"></div> <div id="Pill-react-component-a33f58b8-5572-4fbf-8f8b-18bc1f173928"></div> </a><a data-click-track="profile-user-info-expand-research-interests" data-has-card-for-ri-list="33971246" href="https://www.academia.edu/Documents/in/Music_Teacher_Education"><div class="js-react-on-rails-component" style="display:none" data-component-name="Pill" data-props="{"color":"gray","children":["Music Teacher Education"]}" data-trace="false" data-dom-id="Pill-react-component-26ba5beb-206e-47cd-81d6-0658fa996abe"></div> <div id="Pill-react-component-26ba5beb-206e-47cd-81d6-0658fa996abe"></div> </a></div></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 James Henderson</h3></div><div class="js-work-strip profile--work_container" data-work-id="14976685"><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/14976685/Domain_Adaptation_with_Artificial_Data_for_Semantic_Parsing_of_Speech"><img alt="Research paper thumbnail of Domain Adaptation with Artificial Data for Semantic Parsing of Speech" class="work-thumbnail" src="https://attachments.academia-assets.com/43681468/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/14976685/Domain_Adaptation_with_Artificial_Data_for_Semantic_Parsing_of_Speech">Domain Adaptation with Artificial Data for Semantic Parsing of Speech</a></div><div class="wp-workCard_item"><span>North American Chapter of the Association for Computational Linguistics</span><span>, 2009</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">We adapt a semantic role parser to the do- main of goal-directed speech by creating an artificial...</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">We adapt a semantic role parser to the do- main of goal-directed speech by creating an artificial treebank from an existing text tree- bank. We use a three-component model that includes distributional models from both tar- get and source domains. We show that we im- prove the parser&#39;s performance on utterances collected from human-machine dialogues by training on the artificially</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="ece22554900c773114d33c55824c1d54" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681468,"asset_id":14976685,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681468/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&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="14976685"><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="14976685"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976685; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976685]").text(description); $(".js-view-count[data-work-id=14976685]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976685; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976685']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976685, 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: "ece22554900c773114d33c55824c1d54" } } $('.js-work-strip[data-work-id=14976685]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976685,"title":"Domain Adaptation with Artificial Data for Semantic Parsing of Speech","translated_title":"","metadata":{"abstract":"We adapt a semantic role parser to the do- main of goal-directed speech by creating an artificial treebank from an existing text tree- bank. We use a three-component model that includes distributional models from both tar- get and source domains. We show that we im- prove the parser\u0026#39;s performance on utterances collected from human-machine dialogues by training on the artificially","publication_date":{"day":null,"month":null,"year":2009,"errors":{}},"publication_name":"North American Chapter of the Association for Computational Linguistics"},"translated_abstract":"We adapt a semantic role parser to the do- main of goal-directed speech by creating an artificial treebank from an existing text tree- bank. We use a three-component model that includes distributional models from both tar- get and source domains. We show that we im- prove the parser\u0026#39;s performance on utterances collected from human-machine dialogues by training on the artificially","internal_url":"https://www.academia.edu/14976685/Domain_Adaptation_with_Artificial_Data_for_Semantic_Parsing_of_Speech","translated_internal_url":"","created_at":"2015-08-17T02:32:12.629-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735287,"work_id":14976685,"tagging_user_id":33971246,"tagged_user_id":26057544,"co_author_invite_id":null,"email":"p***1@gmail.com","affiliation":"Universit茅 de Gen猫ve","display_order":0,"name":"Paola Merlo","title":"Domain Adaptation with Artificial Data for Semantic Parsing of Speech"},{"id":4735300,"work_id":14976685,"tagging_user_id":33971246,"tagged_user_id":24919989,"co_author_invite_id":null,"email":"p***o@unige.ch","affiliation":"Universit茅 de Gen猫ve","display_order":4194304,"name":"paola merlo","title":"Domain Adaptation with Artificial Data for Semantic Parsing of Speech"},{"id":4735314,"work_id":14976685,"tagging_user_id":33971246,"tagged_user_id":9598512,"co_author_invite_id":null,"email":"p***b@gmail.com","display_order":6291456,"name":"Paola Merlo","title":"Domain Adaptation with Artificial Data for Semantic Parsing of Speech"},{"id":4735490,"work_id":14976685,"tagging_user_id":33971246,"tagged_user_id":4893055,"co_author_invite_id":null,"email":"l***s@gmail.com","affiliation":"University of Malta","display_order":7340032,"name":"Lonneke van der Plas","title":"Domain Adaptation with Artificial Data for Semantic Parsing of Speech"},{"id":4735520,"work_id":14976685,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1070304,"email":"l***s@unige.ch","display_order":7864320,"name":"L. Van Der Plas","title":"Domain Adaptation with Artificial Data for Semantic Parsing of Speech"}],"downloadable_attachments":[{"id":43681468,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681468/thumbnails/1.jpg","file_name":"N09-2032.pdf","download_url":"https://www.academia.edu/attachments/43681468/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Domain_Adaptation_with_Artificial_Data_f.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681468/N09-2032-libre.pdf?1457873730=\u0026response-content-disposition=attachment%3B+filename%3DDomain_Adaptation_with_Artificial_Data_f.pdf\u0026Expires=1732458746\u0026Signature=I~kcqlimnVf-hROaqRKW7rP88mfXGj5t7aV3bGCmTItNDb8s4ZtuQ9ESvg8XsHCATqZCMtp0VOpCQipieg-I7mhbT2dEZrxcDTrE6RRb2~-x3MLYSxMLkY2QLQw0-LHmxfrt8Xww2~LBn-J8TxG2qUVPWQS5QDQoimHwyqS5q-Pw81NTo2AQfTyd4ne1QLykxMefJqroUToiK4TC-TBSiNS6TFt5XgL1ppi5zsez4vOEdeA8jJYfLPXralyv4H3H4k-kisLJyTwVO0wDXVO7gXrHz7X4tegfjcuDoU~2id6j6YGSXWmYmswaLrsfuOPvSnY61BGshRwFLbULDRcDJA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Domain_Adaptation_with_Artificial_Data_for_Semantic_Parsing_of_Speech","translated_slug":"","page_count":4,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681468,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681468/thumbnails/1.jpg","file_name":"N09-2032.pdf","download_url":"https://www.academia.edu/attachments/43681468/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Domain_Adaptation_with_Artificial_Data_f.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681468/N09-2032-libre.pdf?1457873730=\u0026response-content-disposition=attachment%3B+filename%3DDomain_Adaptation_with_Artificial_Data_f.pdf\u0026Expires=1732458746\u0026Signature=I~kcqlimnVf-hROaqRKW7rP88mfXGj5t7aV3bGCmTItNDb8s4ZtuQ9ESvg8XsHCATqZCMtp0VOpCQipieg-I7mhbT2dEZrxcDTrE6RRb2~-x3MLYSxMLkY2QLQw0-LHmxfrt8Xww2~LBn-J8TxG2qUVPWQS5QDQoimHwyqS5q-Pw81NTo2AQfTyd4ne1QLykxMefJqroUToiK4TC-TBSiNS6TFt5XgL1ppi5zsez4vOEdeA8jJYfLPXralyv4H3H4k-kisLJyTwVO0wDXVO7gXrHz7X4tegfjcuDoU~2id6j6YGSXWmYmswaLrsfuOPvSnY61BGshRwFLbULDRcDJA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":2007534,"name":"Component Model","url":"https://www.academia.edu/Documents/in/Component_Model"}],"urls":[{"id":5217570,"url":"http://www.informatik.uni-trier.de/~ley/db/conf/naacl/naacl2009s.html#PlasHM09"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="14976684"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/14976684/Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning"><img alt="Research paper thumbnail of Undirected Machine Translation with Discriminative Reinforcement Learning" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/14976684/Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning">Undirected Machine Translation with Discriminative Reinforcement Learning</a></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="14976684"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="14976684"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976684; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976684]").text(description); $(".js-view-count[data-work-id=14976684]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976684; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976684']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976684, 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" } } $('.js-work-strip[data-work-id=14976684]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976684,"title":"Undirected Machine Translation with Discriminative Reinforcement Learning","translated_title":"","metadata":{},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976684/Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning","translated_internal_url":"","created_at":"2015-08-17T02:32:12.504-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735410,"work_id":14976684,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083276,"email":"a***o@unige.ch","display_order":0,"name":"Andrea Gesmundo","title":"Undirected Machine Translation with Discriminative Reinforcement Learning"}],"downloadable_attachments":[],"slug":"Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[],"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="14976683"><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/14976683/Incremental_Sigmoid_Belief_Networks_for_Grammar_Learning"><img alt="Research paper thumbnail of Incremental Sigmoid Belief Networks for Grammar Learning" class="work-thumbnail" src="https://attachments.academia-assets.com/43681505/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/14976683/Incremental_Sigmoid_Belief_Networks_for_Grammar_Learning">Incremental Sigmoid Belief Networks for Grammar Learning</a></div><div class="wp-workCard_item"><span>Journal of Machine Learning Research</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">We propose a class of Bayesian networks appropriate for structured prediction problems where the ...</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">We propose a class of Bayesian networks appropriate for structured prediction problems where the Bayesian network&#39;s model structure is a function of the predicted output structure. These incremental sigmoid belief networks (ISBNs) make decoding possible because inference with partial output structures does not require summing over the unboundedly many compatible model structures, due to their directed edges and incrementally specified model structure. ISBNs are specifically targeted at challenging structured prediction problems such as natural language parsing, where learning the domain&#39;s complex statistical dependencies benefits from large numbers of latent variables. While exact inference in ISBNs with large numbers of latent variables is not tractable, we propose two efficient approximations. First, we demonstrate that a previous neural network parsing model can be viewed as a coarse mean-field approximation to inference with ISBNs. We then derive a more accurate but stil...</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="cd274b1f806da461315f75203a06caa8" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681505,"asset_id":14976683,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681505/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&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="14976683"><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="14976683"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976683; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976683]").text(description); $(".js-view-count[data-work-id=14976683]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976683; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976683']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976683, 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: "cd274b1f806da461315f75203a06caa8" } } $('.js-work-strip[data-work-id=14976683]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976683,"title":"Incremental Sigmoid Belief Networks for Grammar Learning","translated_title":"","metadata":{"abstract":"We propose a class of Bayesian networks appropriate for structured prediction problems where the Bayesian network\u0026#39;s model structure is a function of the predicted output structure. These incremental sigmoid belief networks (ISBNs) make decoding possible because inference with partial output structures does not require summing over the unboundedly many compatible model structures, due to their directed edges and incrementally specified model structure. ISBNs are specifically targeted at challenging structured prediction problems such as natural language parsing, where learning the domain\u0026#39;s complex statistical dependencies benefits from large numbers of latent variables. While exact inference in ISBNs with large numbers of latent variables is not tractable, we propose two efficient approximations. First, we demonstrate that a previous neural network parsing model can be viewed as a coarse mean-field approximation to inference with ISBNs. We then derive a more accurate but stil...","publication_name":"Journal of Machine Learning Research"},"translated_abstract":"We propose a class of Bayesian networks appropriate for structured prediction problems where the Bayesian network\u0026#39;s model structure is a function of the predicted output structure. These incremental sigmoid belief networks (ISBNs) make decoding possible because inference with partial output structures does not require summing over the unboundedly many compatible model structures, due to their directed edges and incrementally specified model structure. ISBNs are specifically targeted at challenging structured prediction problems such as natural language parsing, where learning the domain\u0026#39;s complex statistical dependencies benefits from large numbers of latent variables. While exact inference in ISBNs with large numbers of latent variables is not tractable, we propose two efficient approximations. First, we demonstrate that a previous neural network parsing model can be viewed as a coarse mean-field approximation to inference with ISBNs. We then derive a more accurate but stil...","internal_url":"https://www.academia.edu/14976683/Incremental_Sigmoid_Belief_Networks_for_Grammar_Learning","translated_internal_url":"","created_at":"2015-08-17T02:32:12.273-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735504,"work_id":14976683,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":57191,"email":"t***v@mmci.uni-saarland.de","display_order":0,"name":"Ivan Titov","title":"Incremental Sigmoid Belief Networks for Grammar Learning"}],"downloadable_attachments":[{"id":43681505,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681505/thumbnails/1.jpg","file_name":"Incremental_Sigmoid_Belief_Networks_for_20160313-14997-5xzmq2.pdf","download_url":"https://www.academia.edu/attachments/43681505/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Incremental_Sigmoid_Belief_Networks_for.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681505/Incremental_Sigmoid_Belief_Networks_for_20160313-14997-5xzmq2-libre.pdf?1457873730=\u0026response-content-disposition=attachment%3B+filename%3DIncremental_Sigmoid_Belief_Networks_for.pdf\u0026Expires=1732458746\u0026Signature=TrPn15fn8-gjgyccT21efuGQWRgtnpClqvrbJHqjCYy44qu3iNFt1KJ~5xAj4W3Tpl3vvL65H-9H1oDQTvhGZf7GWiye-IYnk5IGOthqrTc6Vs2NA1OkbiK1urvysWWMsBw0qpmjloj--koLhSPlshdmAXkd11VeR0YJCmL51nOQw4Yr3414RvbT-dxj4Eu0R9FPeWOeHEQ5DQp8Pts~5zw~4qoWVnX7O8BMZCDUlPyhkACf1RC3K6JMNBjnDCxtWZuV3umydMEFOLQtm9KfwOJ66uidbb8FHicZ1IeqQcq3ShusohaAYpeYrVSJEQQWqfSE7dolgJBBnzHIB~iIXg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Incremental_Sigmoid_Belief_Networks_for_Grammar_Learning","translated_slug":"","page_count":30,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681505,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681505/thumbnails/1.jpg","file_name":"Incremental_Sigmoid_Belief_Networks_for_20160313-14997-5xzmq2.pdf","download_url":"https://www.academia.edu/attachments/43681505/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Incremental_Sigmoid_Belief_Networks_for.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681505/Incremental_Sigmoid_Belief_Networks_for_20160313-14997-5xzmq2-libre.pdf?1457873730=\u0026response-content-disposition=attachment%3B+filename%3DIncremental_Sigmoid_Belief_Networks_for.pdf\u0026Expires=1732458746\u0026Signature=TrPn15fn8-gjgyccT21efuGQWRgtnpClqvrbJHqjCYy44qu3iNFt1KJ~5xAj4W3Tpl3vvL65H-9H1oDQTvhGZf7GWiye-IYnk5IGOthqrTc6Vs2NA1OkbiK1urvysWWMsBw0qpmjloj--koLhSPlshdmAXkd11VeR0YJCmL51nOQw4Yr3414RvbT-dxj4Eu0R9FPeWOeHEQ5DQp8Pts~5zw~4qoWVnX7O8BMZCDUlPyhkACf1RC3K6JMNBjnDCxtWZuV3umydMEFOLQtm9KfwOJ66uidbb8FHicZ1IeqQcq3ShusohaAYpeYrVSJEQQWqfSE7dolgJBBnzHIB~iIXg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":2008,"name":"Machine Learning","url":"https://www.academia.edu/Documents/in/Machine_Learning"},{"id":663297,"name":"Bayesian Belief Network","url":"https://www.academia.edu/Documents/in/Bayesian_Belief_Network"}],"urls":[{"id":6897528,"url":"https://www.researchgate.net/profile/James_Henderson8/publication/220320210_Incremental_Sigmoid_Belief_Networks_for_Grammar_Learning/links/0deec518b7f3e68091000000.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="14976682"><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/14976682/Temporal_Restricted_Boltzmann_Machines_for_Dependency_Parsing"><img alt="Research paper thumbnail of Temporal Restricted Boltzmann Machines for Dependency Parsing" class="work-thumbnail" src="https://attachments.academia-assets.com/43681521/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/14976682/Temporal_Restricted_Boltzmann_Machines_for_Dependency_Parsing">Temporal Restricted Boltzmann Machines for Dependency Parsing</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">We propose a generative model based on Temporal Restricted Boltzmann Machines for transition base...</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">We propose a generative model based on Temporal Restricted Boltzmann Machines for transition based dependency parsing. The parse tree is built incrementally using a shift-reduce parse and an RBM is used to model each decision step. The RBM at the current time step induces latent features with the help of temporal connections to the relevant previous steps which provide context information. Our parser achieves labeled and unlabeled attachment scores of 88.72% and 91.65% respectively, which compare well with similar previous models and the state-of-the-art.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="b5ba62afb30c37bedd1e533e3ec68fa9" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681521,"asset_id":14976682,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681521/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&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="14976682"><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="14976682"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976682; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976682]").text(description); $(".js-view-count[data-work-id=14976682]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976682; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976682']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976682, 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: "b5ba62afb30c37bedd1e533e3ec68fa9" } } $('.js-work-strip[data-work-id=14976682]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976682,"title":"Temporal Restricted Boltzmann Machines for Dependency Parsing","translated_title":"","metadata":{"abstract":"We propose a generative model based on Temporal Restricted Boltzmann Machines for transition based dependency parsing. The parse tree is built incrementally using a shift-reduce parse and an RBM is used to model each decision step. The RBM at the current time step induces latent features with the help of temporal connections to the relevant previous steps which provide context information. Our parser achieves labeled and unlabeled attachment scores of 88.72% and 91.65% respectively, which compare well with similar previous models and the state-of-the-art."},"translated_abstract":"We propose a generative model based on Temporal Restricted Boltzmann Machines for transition based dependency parsing. The parse tree is built incrementally using a shift-reduce parse and an RBM is used to model each decision step. The RBM at the current time step induces latent features with the help of temporal connections to the relevant previous steps which provide context information. Our parser achieves labeled and unlabeled attachment scores of 88.72% and 91.65% respectively, which compare well with similar previous models and the state-of-the-art.","internal_url":"https://www.academia.edu/14976682/Temporal_Restricted_Boltzmann_Machines_for_Dependency_Parsing","translated_internal_url":"","created_at":"2015-08-17T02:32:12.078-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735524,"work_id":14976682,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083285,"email":"n***g@unige.ch","display_order":0,"name":"N. Garg","title":"Temporal Restricted Boltzmann Machines for Dependency Parsing"}],"downloadable_attachments":[{"id":43681521,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681521/thumbnails/1.jpg","file_name":"Temporal_Restricted_Boltzmann_Machines_f20160313-2737-14s3nuu.pdf","download_url":"https://www.academia.edu/attachments/43681521/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Temporal_Restricted_Boltzmann_Machines_f.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681521/Temporal_Restricted_Boltzmann_Machines_f20160313-2737-14s3nuu-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DTemporal_Restricted_Boltzmann_Machines_f.pdf\u0026Expires=1732458746\u0026Signature=LeQ42vlMpQHYdz4-8WWKMy9~-8eCa3FN6jaK48MMIZe1YaFkf7zLTlmTTqlcYD2Bh6B1A87Kh00s8CFyeU58fgfX0vAMa-MkF53mBXQ42AOWAsA5pDaYqzEdG4BIFaWRzcTI-Bbj326GveGbkTYJfN~lFt0wJX7h7d2DHNADiaavDjpS~pMaR5PEepsOq7TKRscVMXRd8D6s5k3OrrACYkGrgLG7UrcWxzezb2iCBCpQTV-w9OTKwu96K-pTrJ4KGcM6r1i8hdbWRrBE1lrcKExntONYsNlItSHnmmCln8i7HY3UJvXmVr8gU1Qx0ObnhhgqGm3PJ2nt2VbSz2QbIg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Temporal_Restricted_Boltzmann_Machines_for_Dependency_Parsing","translated_slug":"","page_count":55,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681521,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681521/thumbnails/1.jpg","file_name":"Temporal_Restricted_Boltzmann_Machines_f20160313-2737-14s3nuu.pdf","download_url":"https://www.academia.edu/attachments/43681521/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Temporal_Restricted_Boltzmann_Machines_f.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681521/Temporal_Restricted_Boltzmann_Machines_f20160313-2737-14s3nuu-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DTemporal_Restricted_Boltzmann_Machines_f.pdf\u0026Expires=1732458746\u0026Signature=LeQ42vlMpQHYdz4-8WWKMy9~-8eCa3FN6jaK48MMIZe1YaFkf7zLTlmTTqlcYD2Bh6B1A87Kh00s8CFyeU58fgfX0vAMa-MkF53mBXQ42AOWAsA5pDaYqzEdG4BIFaWRzcTI-Bbj326GveGbkTYJfN~lFt0wJX7h7d2DHNADiaavDjpS~pMaR5PEepsOq7TKRscVMXRd8D6s5k3OrrACYkGrgLG7UrcWxzezb2iCBCpQTV-w9OTKwu96K-pTrJ4KGcM6r1i8hdbWRrBE1lrcKExntONYsNlItSHnmmCln8i7HY3UJvXmVr8gU1Qx0ObnhhgqGm3PJ2nt2VbSz2QbIg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":2008,"name":"Machine Learning","url":"https://www.academia.edu/Documents/in/Machine_Learning"},{"id":322355,"name":"RBM","url":"https://www.academia.edu/Documents/in/RBM"}],"urls":[{"id":6897530,"url":"https://www.researchgate.net/profile/James_Henderson8/publication/220874210_Temporal_Restricted_Boltzmann_Machines_for_Dependency_Parsing/links/551aec310cf2bb7540786dbc.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="14976681"><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/14976681/Scaling_up_Automatic_Cross_Lingual_Semantic_Role_Annotation"><img alt="Research paper thumbnail of Scaling up Automatic Cross-Lingual Semantic Role Annotation" class="work-thumbnail" src="https://attachments.academia-assets.com/43681467/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/14976681/Scaling_up_Automatic_Cross_Lingual_Semantic_Role_Annotation">Scaling up Automatic Cross-Lingual Semantic Role Annotation</a></div><div class="wp-workCard_item wp-workCard--coauthors"><span>by </span><span><a class="" data-click-track="profile-work-strip-authors" href="https://independent.academia.edu/JamesHenderson28">James Henderson</a> and <a class="" data-click-track="profile-work-strip-authors" href="https://unige.academia.edu/paolamerlo">paola merlo</a></span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Broad-coverage semantic annotations for training statistical learners are only available for a ha...</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">Broad-coverage semantic annotations for training statistical learners are only available for a handful of languages. Previous approaches to cross-lingual transfer of semantic annotations have addressed this problem with encouraging results on a small scale. In this paper, we scale up previous efforts by using an automatic approach to semantic annotation that does not rely on a semantic ontology for the target language. Moreover, we improve the quality of the transferred semantic annotations by using a joint syntactic-semantic parser that learns the correlations between syntax and semantics of the target language and smooths out the errors from automatic transfer. We reach a labelled F-measure for predicates and arguments of only 4% and 9% points, respectively, lower than the upper bound from manual annotations.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="be07c39a564b093bd62c1283399962d2" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681467,"asset_id":14976681,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681467/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&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="14976681"><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="14976681"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976681; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976681]").text(description); $(".js-view-count[data-work-id=14976681]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976681; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976681']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976681, 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: "be07c39a564b093bd62c1283399962d2" } } $('.js-work-strip[data-work-id=14976681]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976681,"title":"Scaling up Automatic Cross-Lingual Semantic Role Annotation","translated_title":"","metadata":{"abstract":"Broad-coverage semantic annotations for training statistical learners are only available for a handful of languages. Previous approaches to cross-lingual transfer of semantic annotations have addressed this problem with encouraging results on a small scale. In this paper, we scale up previous efforts by using an automatic approach to semantic annotation that does not rely on a semantic ontology for the target language. Moreover, we improve the quality of the transferred semantic annotations by using a joint syntactic-semantic parser that learns the correlations between syntax and semantics of the target language and smooths out the errors from automatic transfer. We reach a labelled F-measure for predicates and arguments of only 4% and 9% points, respectively, lower than the upper bound from manual annotations."},"translated_abstract":"Broad-coverage semantic annotations for training statistical learners are only available for a handful of languages. Previous approaches to cross-lingual transfer of semantic annotations have addressed this problem with encouraging results on a small scale. In this paper, we scale up previous efforts by using an automatic approach to semantic annotation that does not rely on a semantic ontology for the target language. Moreover, we improve the quality of the transferred semantic annotations by using a joint syntactic-semantic parser that learns the correlations between syntax and semantics of the target language and smooths out the errors from automatic transfer. We reach a labelled F-measure for predicates and arguments of only 4% and 9% points, respectively, lower than the upper bound from manual annotations.","internal_url":"https://www.academia.edu/14976681/Scaling_up_Automatic_Cross_Lingual_Semantic_Role_Annotation","translated_internal_url":"","created_at":"2015-08-17T02:32:11.872-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735288,"work_id":14976681,"tagging_user_id":33971246,"tagged_user_id":26057544,"co_author_invite_id":null,"email":"p***1@gmail.com","affiliation":"Universit茅 de Gen猫ve","display_order":0,"name":"Paola Merlo","title":"Scaling up Automatic Cross-Lingual Semantic Role Annotation"},{"id":4735301,"work_id":14976681,"tagging_user_id":33971246,"tagged_user_id":24919989,"co_author_invite_id":null,"email":"p***o@unige.ch","affiliation":"Universit茅 de Gen猫ve","display_order":4194304,"name":"paola merlo","title":"Scaling up Automatic Cross-Lingual Semantic Role Annotation"},{"id":4735315,"work_id":14976681,"tagging_user_id":33971246,"tagged_user_id":9598512,"co_author_invite_id":null,"email":"p***b@gmail.com","display_order":6291456,"name":"Paola Merlo","title":"Scaling up Automatic Cross-Lingual Semantic Role Annotation"},{"id":4735491,"work_id":14976681,"tagging_user_id":33971246,"tagged_user_id":4893055,"co_author_invite_id":null,"email":"l***s@gmail.com","affiliation":"University of Malta","display_order":7340032,"name":"Lonneke van der Plas","title":"Scaling up Automatic Cross-Lingual Semantic Role Annotation"},{"id":4735521,"work_id":14976681,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1070304,"email":"l***s@unige.ch","display_order":7864320,"name":"L. Van Der Plas","title":"Scaling up Automatic Cross-Lingual Semantic Role Annotation"}],"downloadable_attachments":[{"id":43681467,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681467/thumbnails/1.jpg","file_name":"Scaling_up_Automatic_Cross-Lingual_Seman20160313-2737-1kfcljb.pdf","download_url":"https://www.academia.edu/attachments/43681467/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Scaling_up_Automatic_Cross_Lingual_Seman.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681467/Scaling_up_Automatic_Cross-Lingual_Seman20160313-2737-1kfcljb-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DScaling_up_Automatic_Cross_Lingual_Seman.pdf\u0026Expires=1732458746\u0026Signature=CCZV0OuRXfYEOagnE-qNf4XhdSuDQlp6Jm3~e-wBvGFLBPpADZVGrtCG4cib2M5ZGkr8vX3mC60N6Xh-YvuS6AON4~W2ZPNe7a8TODuKCJcWwFAuTGk~YZa08~oEqdmu~pThv13wD80iNl9PJxUAjs6uUoRSeTa383wH4JfNmE4I6HdCQJ1n86aUWNGWy5ObqplEHsN6l9MR-uSwxXVJKv7Jc-I9WGJyL217lhgLXbdXSwDAsG4uErrc8-6ZByEOYFG5WpiveqVqZcQyx9oJ-HQBo3wlSBEsFbg8gPwcqA9SWLnsRjU~Lq7DAXYVnG7GBdgWKnvX~v8fVwSGyo785g__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Scaling_up_Automatic_Cross_Lingual_Semantic_Role_Annotation","translated_slug":"","page_count":6,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681467,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681467/thumbnails/1.jpg","file_name":"Scaling_up_Automatic_Cross-Lingual_Seman20160313-2737-1kfcljb.pdf","download_url":"https://www.academia.edu/attachments/43681467/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Scaling_up_Automatic_Cross_Lingual_Seman.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681467/Scaling_up_Automatic_Cross-Lingual_Seman20160313-2737-1kfcljb-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DScaling_up_Automatic_Cross_Lingual_Seman.pdf\u0026Expires=1732458746\u0026Signature=CCZV0OuRXfYEOagnE-qNf4XhdSuDQlp6Jm3~e-wBvGFLBPpADZVGrtCG4cib2M5ZGkr8vX3mC60N6Xh-YvuS6AON4~W2ZPNe7a8TODuKCJcWwFAuTGk~YZa08~oEqdmu~pThv13wD80iNl9PJxUAjs6uUoRSeTa383wH4JfNmE4I6HdCQJ1n86aUWNGWy5ObqplEHsN6l9MR-uSwxXVJKv7Jc-I9WGJyL217lhgLXbdXSwDAsG4uErrc8-6ZByEOYFG5WpiveqVqZcQyx9oJ-HQBo3wlSBEsFbg8gPwcqA9SWLnsRjU~Lq7DAXYVnG7GBdgWKnvX~v8fVwSGyo785g__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[],"urls":[{"id":6897525,"url":"https://www.researchgate.net/profile/James_Henderson8/publication/220874897_Scaling_up_Automatic_Cross-Lingual_Semantic_Role_Annotation/links/0deec518b7f39257e3000000.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="14976679"><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/14976679/Heuristic_Search_for_Non_Bottom_Up_Tree_Structure_Prediction"><img alt="Research paper thumbnail of Heuristic Search for Non-Bottom-Up Tree Structure Prediction" class="work-thumbnail" src="https://attachments.academia-assets.com/43681509/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/14976679/Heuristic_Search_for_Non_Bottom_Up_Tree_Structure_Prediction">Heuristic Search for Non-Bottom-Up Tree Structure Prediction</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">State of the art Tree Structures Prediction techniques rely on bottom-up decoding. These approach...</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 Tree Structures Prediction techniques rely on bottom-up decoding. These approaches allow the use of context-free features and bottom-up features. We discuss the limitations of mainstream techniques in solving common Natural Language Processing tasks. Then we devise a new framework that goes beyond Bottom-up Decoding, and that allows a better integration of contextual features. Furthermore we design a system that addresses these issues and we test it on Hierarchical Machine Translation, a well known tree structure prediction problem. The structure of the proposed system allows the incorporation of non-bottom-up features and relies on a more sophisticated decoding approach. We show that the proposed approach can find better translations using a smaller portion of the search space.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="abb1b7b69f8112dc0f3a3608323254d4" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681509,"asset_id":14976679,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681509/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&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="14976679"><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="14976679"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976679; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976679]").text(description); $(".js-view-count[data-work-id=14976679]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976679; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976679']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976679, 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: "abb1b7b69f8112dc0f3a3608323254d4" } } $('.js-work-strip[data-work-id=14976679]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976679,"title":"Heuristic Search for Non-Bottom-Up Tree Structure Prediction","translated_title":"","metadata":{"abstract":"State of the art Tree Structures Prediction techniques rely on bottom-up decoding. These approaches allow the use of context-free features and bottom-up features. We discuss the limitations of mainstream techniques in solving common Natural Language Processing tasks. Then we devise a new framework that goes beyond Bottom-up Decoding, and that allows a better integration of contextual features. Furthermore we design a system that addresses these issues and we test it on Hierarchical Machine Translation, a well known tree structure prediction problem. The structure of the proposed system allows the incorporation of non-bottom-up features and relies on a more sophisticated decoding approach. We show that the proposed approach can find better translations using a smaller portion of the search space."},"translated_abstract":"State of the art Tree Structures Prediction techniques rely on bottom-up decoding. These approaches allow the use of context-free features and bottom-up features. We discuss the limitations of mainstream techniques in solving common Natural Language Processing tasks. Then we devise a new framework that goes beyond Bottom-up Decoding, and that allows a better integration of contextual features. Furthermore we design a system that addresses these issues and we test it on Hierarchical Machine Translation, a well known tree structure prediction problem. The structure of the proposed system allows the incorporation of non-bottom-up features and relies on a more sophisticated decoding approach. We show that the proposed approach can find better translations using a smaller portion of the search space.","internal_url":"https://www.academia.edu/14976679/Heuristic_Search_for_Non_Bottom_Up_Tree_Structure_Prediction","translated_internal_url":"","created_at":"2015-08-17T02:32:11.718-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735408,"work_id":14976679,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083276,"email":"a***o@unige.ch","display_order":0,"name":"Andrea Gesmundo","title":"Heuristic Search for Non-Bottom-Up Tree Structure Prediction"}],"downloadable_attachments":[{"id":43681509,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681509/thumbnails/1.jpg","file_name":"Heuristic_Search_for_Non-Bottom-Up_Tree_20160313-15496-bdxe3r.pdf","download_url":"https://www.academia.edu/attachments/43681509/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Heuristic_Search_for_Non_Bottom_Up_Tree.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681509/Heuristic_Search_for_Non-Bottom-Up_Tree_20160313-15496-bdxe3r-libre.pdf?1457873729=\u0026response-content-disposition=attachment%3B+filename%3DHeuristic_Search_for_Non_Bottom_Up_Tree.pdf\u0026Expires=1732458746\u0026Signature=fpJinabkCUCm8u-wB3QgcuYLLRRCw6091UJK-pNYBzNn1pLWibZ5KogE68-xeXfwnLvigAEThJK83SIduDMqYRbuJZ0LlrO3tThDX7xMeWuVdokXSmbzdVsO9BNPU4EP2wSw1mg5w4s116qpWpfxgPlSbo20pzvG5TKHC0Brm9LS3PQh6BFxHWQbfLctY5S1lodFYQs02CCf9mWQZO6LE0G3IgpdnqP8NwvwRelYwhkOCeUpSQMnLCwwNTJvOpF4ydjaQqqRP9YAq7eAzQvGzX9vKpCEPMO7PIy55sUh5eaNH9TfsKiaElb4lT6qnvrCYxN4n7x3ydO0trCKli0Onw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Heuristic_Search_for_Non_Bottom_Up_Tree_Structure_Prediction","translated_slug":"","page_count":10,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681509,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681509/thumbnails/1.jpg","file_name":"Heuristic_Search_for_Non-Bottom-Up_Tree_20160313-15496-bdxe3r.pdf","download_url":"https://www.academia.edu/attachments/43681509/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Heuristic_Search_for_Non_Bottom_Up_Tree.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681509/Heuristic_Search_for_Non-Bottom-Up_Tree_20160313-15496-bdxe3r-libre.pdf?1457873729=\u0026response-content-disposition=attachment%3B+filename%3DHeuristic_Search_for_Non_Bottom_Up_Tree.pdf\u0026Expires=1732458746\u0026Signature=fpJinabkCUCm8u-wB3QgcuYLLRRCw6091UJK-pNYBzNn1pLWibZ5KogE68-xeXfwnLvigAEThJK83SIduDMqYRbuJZ0LlrO3tThDX7xMeWuVdokXSmbzdVsO9BNPU4EP2wSw1mg5w4s116qpWpfxgPlSbo20pzvG5TKHC0Brm9LS3PQh6BFxHWQbfLctY5S1lodFYQs02CCf9mWQZO6LE0G3IgpdnqP8NwvwRelYwhkOCeUpSQMnLCwwNTJvOpF4ydjaQqqRP9YAq7eAzQvGzX9vKpCEPMO7PIy55sUh5eaNH9TfsKiaElb4lT6qnvrCYxN4n7x3ydO0trCKli0Onw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[],"urls":[{"id":6897529,"url":"https://www.researchgate.net/profile/James_Henderson8/publication/221013234_Heuristic_Search_for_Non-Bottom-Up_Tree_Structure_Prediction/links/00b49518b81d715307000000.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="14976678"><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/14976678/Unsupervised_semantic_role_induction_with_global_role_ordering"><img alt="Research paper thumbnail of Unsupervised semantic role induction with global role ordering" class="work-thumbnail" src="https://attachments.academia-assets.com/43681472/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/14976678/Unsupervised_semantic_role_induction_with_global_role_ordering">Unsupervised semantic role induction with global role ordering</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">We propose a probabilistic generative model for unsupervised semantic role induction, which integ...</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">We propose a probabilistic generative model for unsupervised semantic role induction, which integrates local role assignment decisions and a global role ordering decision in a unified model. The role sequence is divided into intervals based on the notion of primary roles, and each interval generates a sequence of secondary roles and syntactic constituents using local features. The global role ordering consists of the sequence of primary roles only, thus making it a partial ordering.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="47ff8e78ff1972bfdaf486d78eebe289" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681472,"asset_id":14976678,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681472/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&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="14976678"><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="14976678"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976678; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976678]").text(description); $(".js-view-count[data-work-id=14976678]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976678; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976678']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976678, 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: "47ff8e78ff1972bfdaf486d78eebe289" } } $('.js-work-strip[data-work-id=14976678]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976678,"title":"Unsupervised semantic role induction with global role ordering","translated_title":"","metadata":{"abstract":"We propose a probabilistic generative model for unsupervised semantic role induction, which integrates local role assignment decisions and a global role ordering decision in a unified model. The role sequence is divided into intervals based on the notion of primary roles, and each interval generates a sequence of secondary roles and syntactic constituents using local features. The global role ordering consists of the sequence of primary roles only, thus making it a partial ordering."},"translated_abstract":"We propose a probabilistic generative model for unsupervised semantic role induction, which integrates local role assignment decisions and a global role ordering decision in a unified model. The role sequence is divided into intervals based on the notion of primary roles, and each interval generates a sequence of secondary roles and syntactic constituents using local features. The global role ordering consists of the sequence of primary roles only, thus making it a partial ordering.","internal_url":"https://www.academia.edu/14976678/Unsupervised_semantic_role_induction_with_global_role_ordering","translated_internal_url":"","created_at":"2015-08-17T02:32:11.580-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735523,"work_id":14976678,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083285,"email":"n***g@unige.ch","display_order":0,"name":"N. Garg","title":"Unsupervised semantic role induction with global role ordering"}],"downloadable_attachments":[{"id":43681472,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681472/thumbnails/1.jpg","file_name":"Unsupervised_semantic_role_induction_wit20160313-6133-9j9gn1.pdf","download_url":"https://www.academia.edu/attachments/43681472/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Unsupervised_semantic_role_induction_wit.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681472/Unsupervised_semantic_role_induction_wit20160313-6133-9j9gn1-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DUnsupervised_semantic_role_induction_wit.pdf\u0026Expires=1732458746\u0026Signature=eUDbrm2s1XhQzLqnGY-u2ckHK9B3K-Zb9bAYq7a-PsLmgEC30lce8EYTIYls9Z~w0l~nV-75Ed8z0tVyTqqrLh8y5R0T6uJKhn-jkJinS8tz01m941STEz8Qsu6wuTkLpfjvvAuOtbFgOLoa2LMxVCFb2J5uoTQUNnGqTGbC4gTekVqF2ce3lBkbA4Zj1jOMq1YFjIhYWuDp8Yvndd2YdfLCjBSSGRGzfyLMvpwhhAWQKoAZPfDZwaxnyA0rYDqmdZjSs3hIqc79WU-WzmUK15mpVZENWARlMScN2l72PtdXzWIjKC60TRqBxMVVKS0JjDrQsi69HeAvaHhi8nLhiA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Unsupervised_semantic_role_induction_with_global_role_ordering","translated_slug":"","page_count":5,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681472,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681472/thumbnails/1.jpg","file_name":"Unsupervised_semantic_role_induction_wit20160313-6133-9j9gn1.pdf","download_url":"https://www.academia.edu/attachments/43681472/download_file?st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Unsupervised_semantic_role_induction_wit.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681472/Unsupervised_semantic_role_induction_wit20160313-6133-9j9gn1-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DUnsupervised_semantic_role_induction_wit.pdf\u0026Expires=1732458746\u0026Signature=eUDbrm2s1XhQzLqnGY-u2ckHK9B3K-Zb9bAYq7a-PsLmgEC30lce8EYTIYls9Z~w0l~nV-75Ed8z0tVyTqqrLh8y5R0T6uJKhn-jkJinS8tz01m941STEz8Qsu6wuTkLpfjvvAuOtbFgOLoa2LMxVCFb2J5uoTQUNnGqTGbC4gTekVqF2ce3lBkbA4Zj1jOMq1YFjIhYWuDp8Yvndd2YdfLCjBSSGRGzfyLMvpwhhAWQKoAZPfDZwaxnyA0rYDqmdZjSs3hIqc79WU-WzmUK15mpVZENWARlMScN2l72PtdXzWIjKC60TRqBxMVVKS0JjDrQsi69HeAvaHhi8nLhiA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[],"urls":[{"id":6897526,"url":"https://www.researchgate.net/profile/James_Henderson8/publication/262309398_Unsupervised_semantic_role_induction_with_global_role_ordering/links/551aec300cf251c35b50348a.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="14976677"><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/14976677/The_PARLANCE_mobile_application_for_interactive_search_in_English_and_Mandarin"><img alt="Research paper thumbnail of The PARLANCE mobile application for interactive search in English and Mandarin" 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/14976677/The_PARLANCE_mobile_application_for_interactive_search_in_English_and_Mandarin">The PARLANCE mobile application for interactive search in English and Mandarin</a></div><div class="wp-workCard_item wp-workCard--coauthors"><span>by </span><span><a class="" data-click-track="profile-work-strip-authors" href="https://independent.academia.edu/JamesHenderson28">James Henderson</a>, <a class="" data-click-track="profile-work-strip-authors" href="https://hw.academia.edu/VerenaRieser">Verena Rieser</a>, and <a class="" data-click-track="profile-work-strip-authors" href="https://independent.academia.edu/MajidYazdani4">Majid Yazdani</a></span></div><div class="wp-workCard_item"><span>Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)</span><span>, 2014</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="14976677"><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="14976677"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976677; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976677]").text(description); $(".js-view-count[data-work-id=14976677]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976677; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976677']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976677, 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" } } $('.js-work-strip[data-work-id=14976677]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976677,"title":"The PARLANCE mobile application for interactive search in English and Mandarin","translated_title":"","metadata":{"publication_date":{"day":null,"month":null,"year":2014,"errors":{}},"publication_name":"Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)"},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976677/The_PARLANCE_mobile_application_for_interactive_search_in_English_and_Mandarin","translated_internal_url":"","created_at":"2015-08-17T02:32:11.493-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735374,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":1067708,"co_author_invite_id":null,"email":"v***r@hw.ac.uk","affiliation":"Heriot-Watt University","display_order":6291456,"name":"Verena Rieser","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735383,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":12926397,"co_author_invite_id":null,"email":"s***g@gmail.com","affiliation":"University of Liverpool","display_order":7340032,"name":"steve young","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735393,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":11042832,"co_author_invite_id":null,"email":"d***5@hotmail.com","display_order":7864320,"name":"Steve Young","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735452,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083281,"email":"o***n@hwac.uk","display_order":8126464,"name":"Oliver Lemon","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735471,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":695287,"email":"o***n@inf.ed.ac.uk","display_order":8257536,"name":"Oliver Lemon","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735475,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":510167,"email":"p***a@cs.vu.nl","display_order":8323072,"name":"Peter Mika","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735477,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":19073,"co_author_invite_id":null,"email":"p***s@gmail.com","affiliation":"National Technical University of Athens","display_order":8355840,"name":"Panos Alexopoulos","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735479,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":5458864,"co_author_invite_id":null,"email":"m***0@gmail.com","display_order":8372224,"name":"majid yazdani","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735480,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083282,"email":"h***e@research.att.com","display_order":8380416,"name":"Helen Hastie","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735481,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083283,"email":"h***e@research.att.com","display_order":8384512,"name":"Helen Hastie","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735482,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":154781,"co_author_invite_id":null,"email":"h***e@hw.ac.uk","affiliation":"Heriot-Watt University","display_order":8386560,"name":"Helen Hastie","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735525,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083286,"email":"c***4@cam.ac.uk","display_order":8387584,"name":"Catherine Breslin","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735526,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":695227,"email":"h***l@ed.ac.uk","display_order":8388096,"name":"Heriberto Cuay谩huitl","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735527,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083287,"email":"n***s@googlemail.com","display_order":8388352,"name":"Nina Dethlefs","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735528,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":34652530,"co_author_invite_id":186493,"email":"m***6@cam.ac.uk","display_order":8388480,"name":"M. Ga拧i膰","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735529,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":189144,"email":"b***2@cam.ac.uk","display_order":8388544,"name":"Blaise Thomson","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735530,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083288,"email":"p***4@cam.ac.uk","display_order":8388576,"name":"Pirros Tsiakoulis","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735531,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083289,"email":"b***n@isoco.com","display_order":8388592,"name":"Boris Villazon-terrazas","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735532,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":34068110,"co_author_invite_id":1083290,"email":"m***i@unige.ch","display_order":8388600,"name":"Majid Yazdani","title":"The PARLANCE mobile application for interactive search in English and Mandarin"}],"downloadable_attachments":[],"slug":"The_PARLANCE_mobile_application_for_interactive_search_in_English_and_Mandarin","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[],"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="14976676"><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/14976676/Mixture_model_POMDPs_for_efficient_handling_of_uncertainty_in_dialogue_management"><img alt="Research paper thumbnail of Mixture model POMDPs for efficient handling of uncertainty in dialogue management" class="work-thumbnail" src="https://attachments.academia-assets.com/43681659/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/14976676/Mixture_model_POMDPs_for_efficient_handling_of_uncertainty_in_dialogue_management">Mixture model POMDPs for efficient handling of uncertainty in dialogue management</a></div><div class="wp-workCard_item"><span>Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies Short Papers - HLT '08</span><span>, 2008</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="7110ada4bfb6eb814b68adba26229a76" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681659,"asset_id":14976676,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681659/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976676"><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="14976676"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976676; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976676]").text(description); $(".js-view-count[data-work-id=14976676]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976676; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976676']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976676, 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: "7110ada4bfb6eb814b68adba26229a76" } } $('.js-work-strip[data-work-id=14976676]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976676,"title":"Mixture model POMDPs for efficient handling of uncertainty in dialogue management","translated_title":"","metadata":{"grobid_abstract":"In spoken dialogue systems, Partially Observable Markov Decision Processes (POMDPs) provide a formal framework for making dialogue management decisions under uncertainty, but efficiency and interpretability considerations mean that most current statistical dialogue managers are only MDPs. These MDP systems encode uncertainty explicitly in a single state representation. We formalise such MDP states in terms of distributions over POMDP states, and propose a new dialogue system architecture (Mixture Model POMDPs) which uses mixtures of these distributions to efficiently represent uncertainty. We also provide initial evaluation results (with real users) for this architecture.","publication_date":{"day":null,"month":null,"year":2008,"errors":{}},"publication_name":"Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies Short Papers - HLT '08","grobid_abstract_attachment_id":43681659},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976676/Mixture_model_POMDPs_for_efficient_handling_of_uncertainty_in_dialogue_management","translated_internal_url":"","created_at":"2015-08-17T02:32:11.402-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735447,"work_id":14976676,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083281,"email":"o***n@hwac.uk","display_order":6291456,"name":"Oliver Lemon","title":"Mixture model POMDPs for efficient handling of uncertainty in dialogue management"},{"id":4735467,"work_id":14976676,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":695287,"email":"o***n@inf.ed.ac.uk","display_order":7340032,"name":"Oliver Lemon","title":"Mixture model POMDPs for efficient handling of uncertainty in dialogue management"}],"downloadable_attachments":[{"id":43681659,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681659/thumbnails/1.jpg","file_name":"Mixture_Model_POMDPs_for_Efficient_Handl20160313-4265-jvrivt.pdf","download_url":"https://www.academia.edu/attachments/43681659/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Mixture_model_POMDPs_for_efficient_handl.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681659/Mixture_Model_POMDPs_for_Efficient_Handl20160313-4265-jvrivt-libre.pdf?1457873716=\u0026response-content-disposition=attachment%3B+filename%3DMixture_model_POMDPs_for_efficient_handl.pdf\u0026Expires=1732458746\u0026Signature=WJyGybBF1X23-H05Bp1jI3LBBPta7i~Sw13EFgtZsMPgCE~m-jB97Ub-2wbAt59EZsk3BaB8Cab6Q5eDRwSBOCbgFL3LfHQJwqIp-Q3r-tjiMq4EdF9DVdvqUIq~F-vV5aHdbdLd8ScPX8qh7jMmloWbIGjeDVQaKo6cOKeZ34BkyQekMzoqaMGMkMok0A7SdmJQbh0I~FGPuC6LmjDcTF6UhoYN2-b5EjifxzP-0-2JqOw-5ulouyZ8TXgT9U7BCQ5sENLsZeQbv0j0mdszs~~fpY0CyJPfUewyusedBNBIsPaxLC7y6G43js8DRcZEDWGcFeLpf3C0XybEOroZlA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Mixture_model_POMDPs_for_efficient_handling_of_uncertainty_in_dialogue_management","translated_slug":"","page_count":4,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681659,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681659/thumbnails/1.jpg","file_name":"Mixture_Model_POMDPs_for_Efficient_Handl20160313-4265-jvrivt.pdf","download_url":"https://www.academia.edu/attachments/43681659/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Mixture_model_POMDPs_for_efficient_handl.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681659/Mixture_Model_POMDPs_for_Efficient_Handl20160313-4265-jvrivt-libre.pdf?1457873716=\u0026response-content-disposition=attachment%3B+filename%3DMixture_model_POMDPs_for_efficient_handl.pdf\u0026Expires=1732458747\u0026Signature=Xw6pLfBustuYZ8WFxekf5iHiImDjZdhwud3NwSZm6dmxeEHNNzES7rVuen6qVXmr1A~vRiOXIqwZs1qm4GNqmFSEsX~8se95eeeaYuCdDlXiH8jQIB~UVd0LZLGZOjaNq~L325QmiD1yS3Yh3CyFNP0x1XicC3RCzeF1mMlR2oOD9ZYqPVLy87OVQ6C8xL3fQ43Nl65FLgUhDnrxctybOJ8i-NaAze-12XnI9uJbscpim0Y6uzIreyoCloh8r-SPPWOkCVOTDQMfttgthbhDo-xjh6fKyVRHRVaAvK3qjGPcc5cLIHWU0tBXY2jwuOiyJOvpCDUqRRkyVeK6nPW8Aw__\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":1688,"name":"Reinforcement Learning","url":"https://www.academia.edu/Documents/in/Reinforcement_Learning"},{"id":2008,"name":"Machine Learning","url":"https://www.academia.edu/Documents/in/Machine_Learning"},{"id":3268,"name":"Computational Linguistics","url":"https://www.academia.edu/Documents/in/Computational_Linguistics"},{"id":5337,"name":"Agent Based Simulation","url":"https://www.academia.edu/Documents/in/Agent_Based_Simulation"},{"id":15084,"name":"Statistical machine learning","url":"https://www.academia.edu/Documents/in/Statistical_machine_learning"},{"id":37228,"name":"Multimodal Interfaces","url":"https://www.academia.edu/Documents/in/Multimodal_Interfaces"},{"id":38181,"name":"AI","url":"https://www.academia.edu/Documents/in/AI"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="14976675"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/14976675/Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning"><img alt="Research paper thumbnail of Undirected Machine Translation with Discriminative Reinforcement Learning" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/14976675/Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning">Undirected Machine Translation with Discriminative Reinforcement Learning</a></div><div class="wp-workCard_item"><span>Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics</span><span>, 2014</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="14976675"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="14976675"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976675; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976675]").text(description); $(".js-view-count[data-work-id=14976675]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976675; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976675']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976675, 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" } } $('.js-work-strip[data-work-id=14976675]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976675,"title":"Undirected Machine Translation with Discriminative Reinforcement Learning","translated_title":"","metadata":{"publication_date":{"day":null,"month":null,"year":2014,"errors":{}},"publication_name":"Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics"},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976675/Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning","translated_internal_url":"","created_at":"2015-08-17T02:32:11.300-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735405,"work_id":14976675,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083276,"email":"a***o@unige.ch","display_order":0,"name":"Andrea Gesmundo","title":"Undirected Machine Translation with Discriminative Reinforcement Learning"}],"downloadable_attachments":[],"slug":"Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[],"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="14976674"><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/14976674/Data_Driven_Methods_for_Spoken_Language_Understanding"><img alt="Research paper thumbnail of Data-Driven Methods for Spoken Language Understanding" 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/14976674/Data_Driven_Methods_for_Spoken_Language_Understanding">Data-Driven Methods for Spoken Language Understanding</a></div><div class="wp-workCard_item"><span>Data-Driven Methods for Adaptive Spoken Dialogue Systems</span><span>, 2012</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Spoken dialogue systems need to be able to interpret the spoken input from the user. This is done...</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">Spoken dialogue systems need to be able to interpret the spoken input from the user. This is done by mapping the user&amp;amp;#x27;s spoken utterance to a representation of the meaning of that utterance, and then passing this representation to the dialogue manager. This process begins with the application of automatic speech recognition (ASR) technology, which maps the speech to hypotheses about the sequence of words in the utterance. It is then the job of spoken language understanding (SLU) to map the word recognition hypotheses to ...</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="14976674"><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="14976674"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976674; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976674]").text(description); $(".js-view-count[data-work-id=14976674]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976674; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976674']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976674, 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" } } $('.js-work-strip[data-work-id=14976674]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976674,"title":"Data-Driven Methods for Spoken Language Understanding","translated_title":"","metadata":{"abstract":"Spoken dialogue systems need to be able to interpret the spoken input from the user. This is done by mapping the user\u0026amp;amp;#x27;s spoken utterance to a representation of the meaning of that utterance, and then passing this representation to the dialogue manager. This process begins with the application of automatic speech recognition (ASR) technology, which maps the speech to hypotheses about the sequence of words in the utterance. It is then the job of spoken language understanding (SLU) to map the word recognition hypotheses to ...","publication_date":{"day":null,"month":null,"year":2012,"errors":{}},"publication_name":"Data-Driven Methods for Adaptive Spoken Dialogue Systems"},"translated_abstract":"Spoken dialogue systems need to be able to interpret the spoken input from the user. This is done by mapping the user\u0026amp;amp;#x27;s spoken utterance to a representation of the meaning of that utterance, and then passing this representation to the dialogue manager. This process begins with the application of automatic speech recognition (ASR) technology, which maps the speech to hypotheses about the sequence of words in the utterance. It is then the job of spoken language understanding (SLU) to map the word recognition hypotheses to ...","internal_url":"https://www.academia.edu/14976674/Data_Driven_Methods_for_Spoken_Language_Understanding","translated_internal_url":"","created_at":"2015-08-17T02:32:11.203-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735426,"work_id":14976674,"tagging_user_id":33971246,"tagged_user_id":1230797,"co_author_invite_id":null,"email":"f***k@gmail.com","affiliation":"Charles University, Prague","display_order":0,"name":"Filip Jurcicek","title":"Data-Driven Methods for Spoken Language Understanding"}],"downloadable_attachments":[],"slug":"Data_Driven_Methods_for_Spoken_Language_Understanding","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="14976673"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/14976673/Graph_Based_Seed_Set_Expansion_for_Relation_Extraction_Using_Random_Walk_Hitting_Times"><img alt="Research paper thumbnail of Graph-Based Seed Set Expansion for Relation Extraction Using Random Walk Hitting Times" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/14976673/Graph_Based_Seed_Set_Expansion_for_Relation_Extraction_Using_Random_Walk_Hitting_Times">Graph-Based Seed Set Expansion for Relation Extraction Using Random Walk Hitting Times</a></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="14976673"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="14976673"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976673; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976673]").text(description); $(".js-view-count[data-work-id=14976673]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976673; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976673']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976673, 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" } } $('.js-work-strip[data-work-id=14976673]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976673,"title":"Graph-Based Seed Set Expansion for Relation Extraction Using Random Walk Hitting Times","translated_title":"","metadata":{},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976673/Graph_Based_Seed_Set_Expansion_for_Relation_Extraction_Using_Random_Walk_Hitting_Times","translated_internal_url":"","created_at":"2015-08-17T02:32:11.118-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735535,"work_id":14976673,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1011476,"email":"s***0@sms.ed.ac.uk","display_order":0,"name":"Joel Lang","title":"Graph-Based Seed Set Expansion for Relation Extraction Using Random Walk Hitting Times"}],"downloadable_attachments":[],"slug":"Graph_Based_Seed_Set_Expansion_for_Relation_Extraction_Using_Random_Walk_Hitting_Times","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[],"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="14976672"><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/14976672/Efficient_Computation_of_Mean_Truncated_Hitting_Times_on_Very_Large_Graphs"><img alt="Research paper thumbnail of Efficient Computation of Mean Truncated Hitting Times on Very Large Graphs" 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/14976672/Efficient_Computation_of_Mean_Truncated_Hitting_Times_on_Very_Large_Graphs">Efficient Computation of Mean Truncated Hitting Times on Very Large Graphs</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">ABSTRACT Previous work has shown the effectiveness of random walk hitting times as a measure of d...</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 Previous work has shown the effectiveness of random walk hitting times as a measure of dissimilarity in a variety of graph-based learning problems such as collaborative filtering, query suggestion or finding paraphrases. However, application of hitting times has been limited to small datasets because of computational restrictions. This paper develops a new approximation algorithm with which hitting times can be computed on very large, disk-resident graphs, making their application possible to problems which were previously out of reach. This will potentially benefit a range of large-scale problems.</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="14976672"><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="14976672"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976672; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976672]").text(description); $(".js-view-count[data-work-id=14976672]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976672; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976672']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976672, 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" } } $('.js-work-strip[data-work-id=14976672]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976672,"title":"Efficient Computation of Mean Truncated Hitting Times on Very Large Graphs","translated_title":"","metadata":{"abstract":"ABSTRACT Previous work has shown the effectiveness of random walk hitting times as a measure of dissimilarity in a variety of graph-based learning problems such as collaborative filtering, query suggestion or finding paraphrases. However, application of hitting times has been limited to small datasets because of computational restrictions. This paper develops a new approximation algorithm with which hitting times can be computed on very large, disk-resident graphs, making their application possible to problems which were previously out of reach. This will potentially benefit a range of large-scale problems."},"translated_abstract":"ABSTRACT Previous work has shown the effectiveness of random walk hitting times as a measure of dissimilarity in a variety of graph-based learning problems such as collaborative filtering, query suggestion or finding paraphrases. However, application of hitting times has been limited to small datasets because of computational restrictions. This paper develops a new approximation algorithm with which hitting times can be computed on very large, disk-resident graphs, making their application possible to problems which were previously out of reach. This will potentially benefit a range of large-scale problems.","internal_url":"https://www.academia.edu/14976672/Efficient_Computation_of_Mean_Truncated_Hitting_Times_on_Very_Large_Graphs","translated_internal_url":"","created_at":"2015-08-17T02:32:11.030-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735534,"work_id":14976672,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1011476,"email":"s***0@sms.ed.ac.uk","display_order":0,"name":"Joel Lang","title":"Efficient Computation of Mean Truncated Hitting Times on Very Large Graphs"}],"downloadable_attachments":[],"slug":"Efficient_Computation_of_Mean_Truncated_Hitting_Times_on_Very_Large_Graphs","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[],"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="14976671"><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/14976671/Automatic_annotation_of_COMMUNICATOR_dialogue_data_for_learning_dialogue_strategies_and_user_simulations"><img alt="Research paper thumbnail of Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations" class="work-thumbnail" src="https://attachments.academia-assets.com/43681660/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/14976671/Automatic_annotation_of_COMMUNICATOR_dialogue_data_for_learning_dialogue_strategies_and_user_simulations">Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations</a></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="6fa09afa279d79c4c97bb86de0b5e528" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681660,"asset_id":14976671,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681660/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976671"><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="14976671"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976671; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976671]").text(description); $(".js-view-count[data-work-id=14976671]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976671; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976671']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976671, 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: "6fa09afa279d79c4c97bb86de0b5e528" } } $('.js-work-strip[data-work-id=14976671]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976671,"title":"Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations","translated_title":"","metadata":{"grobid_abstract":"We present and evaluate an automatic annotation system which builds \"Information State Update\" (ISU) representations of dialogue context for the COMMUNICATOR (2000 and 2001) corpora of humanmachine dialogues (approx 2300 dialogues). The purposes of this annotation are to generate training data for reinforcement learning (RL) of dialogue policies, to generate data for building user simulations, and to evaluate different dialogue strategies against a baseline. The automatic annotation system uses the DIPPER dialogue manager. This produces annotations of user inputs and dialogue context representations. We present a detailed example, and then evaluate our annotations, with respect to the task completion metrics of the original corpus. The resulting data has been used to train user simulations and to learn successful dialogue strategies.","publication_date":{"day":null,"month":null,"year":2005,"errors":{}},"grobid_abstract_attachment_id":43681660},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976671/Automatic_annotation_of_COMMUNICATOR_dialogue_data_for_learning_dialogue_strategies_and_user_simulations","translated_internal_url":"","created_at":"2015-08-17T02:32:10.937-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735455,"work_id":14976671,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083281,"email":"o***n@hwac.uk","display_order":6291456,"name":"Oliver Lemon","title":"Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations"},{"id":4735474,"work_id":14976671,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":695287,"email":"o***n@inf.ed.ac.uk","display_order":7340032,"name":"Oliver Lemon","title":"Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations"},{"id":4735515,"work_id":14976671,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":114196,"email":"k***a@ict.usc.edu","display_order":7864320,"name":"Kallirroi Georgila","title":"Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations"}],"downloadable_attachments":[{"id":43681660,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681660/thumbnails/1.jpg","file_name":"08-Lemon.pdf","download_url":"https://www.academia.edu/attachments/43681660/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Automatic_annotation_of_COMMUNICATOR_dia.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681660/08-Lemon-libre.pdf?1457873716=\u0026response-content-disposition=attachment%3B+filename%3DAutomatic_annotation_of_COMMUNICATOR_dia.pdf\u0026Expires=1732458747\u0026Signature=AA5LZmUTT4a8hr~LBKgGf79jlAtF7TMLrVatcraM-DAU~X6Vtc-knKDaScsyX8apaMXO8ee4QbCnPAMJ2XLseBLMAUMjd-TSz0zJjeqdXhnqBfQ-QPAV8~ayf08AqhWM4VKh7mj4V3QEdMJ4HnTgS6F4hBH1EkFzjKU974rYveXpPIKsuCAvChs30WTQg7Iw0jtvWB5myXOEmlIMmNPP~UigExA4mm82-XMeZMR188rxDThuVoxVem0EkQ~0haYO1dvlzhOJZH0kkj9Bt8iwKnGYbyZiDw7foD-pHuv6O7E60c9F7ti8GZPmNDbjOaP8U5607Am3ID1iDvslN46xPw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Automatic_annotation_of_COMMUNICATOR_dialogue_data_for_learning_dialogue_strategies_and_user_simulations","translated_slug":"","page_count":8,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681660,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681660/thumbnails/1.jpg","file_name":"08-Lemon.pdf","download_url":"https://www.academia.edu/attachments/43681660/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Automatic_annotation_of_COMMUNICATOR_dia.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681660/08-Lemon-libre.pdf?1457873716=\u0026response-content-disposition=attachment%3B+filename%3DAutomatic_annotation_of_COMMUNICATOR_dia.pdf\u0026Expires=1732458747\u0026Signature=AA5LZmUTT4a8hr~LBKgGf79jlAtF7TMLrVatcraM-DAU~X6Vtc-knKDaScsyX8apaMXO8ee4QbCnPAMJ2XLseBLMAUMjd-TSz0zJjeqdXhnqBfQ-QPAV8~ayf08AqhWM4VKh7mj4V3QEdMJ4HnTgS6F4hBH1EkFzjKU974rYveXpPIKsuCAvChs30WTQg7Iw0jtvWB5myXOEmlIMmNPP~UigExA4mm82-XMeZMR188rxDThuVoxVem0EkQ~0haYO1dvlzhOJZH0kkj9Bt8iwKnGYbyZiDw7foD-pHuv6O7E60c9F7ti8GZPmNDbjOaP8U5607Am3ID1iDvslN46xPw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"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":1688,"name":"Reinforcement Learning","url":"https://www.academia.edu/Documents/in/Reinforcement_Learning"},{"id":2008,"name":"Machine Learning","url":"https://www.academia.edu/Documents/in/Machine_Learning"},{"id":5337,"name":"Agent Based Simulation","url":"https://www.academia.edu/Documents/in/Agent_Based_Simulation"},{"id":37228,"name":"Multimodal Interfaces","url":"https://www.academia.edu/Documents/in/Multimodal_Interfaces"},{"id":38181,"name":"AI","url":"https://www.academia.edu/Documents/in/AI"},{"id":1900565,"name":"Automatic Annotation","url":"https://www.academia.edu/Documents/in/Automatic_Annotation"}],"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="14976670"><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/14976670/Final_Report_on_Multimodal_Experiments_Part_II_Experiments_for_data_collection_and_technology_evaluation"><img alt="Research paper thumbnail of Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation" class="work-thumbnail" src="https://attachments.academia-assets.com/43681463/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/14976670/Final_Report_on_Multimodal_Experiments_Part_II_Experiments_for_data_collection_and_technology_evaluation">Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation</a></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="38f052ab146cdb23984c936a4d724541" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681463,"asset_id":14976670,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681463/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976670"><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="14976670"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976670; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976670]").text(description); $(".js-view-count[data-work-id=14976670]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976670; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976670']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976670, 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: "38f052ab146cdb23984c936a4d724541" } } $('.js-work-strip[data-work-id=14976670]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976670,"title":"Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation","translated_title":"","metadata":{"publication_date":{"day":null,"month":null,"year":2006,"errors":{}}},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976670/Final_Report_on_Multimodal_Experiments_Part_II_Experiments_for_data_collection_and_technology_evaluation","translated_internal_url":"","created_at":"2015-08-17T02:32:10.817-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735376,"work_id":14976670,"tagging_user_id":33971246,"tagged_user_id":1067708,"co_author_invite_id":null,"email":"v***r@hw.ac.uk","affiliation":"Heriot-Watt University","display_order":6291456,"name":"Verena Rieser","title":"Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation"},{"id":4735454,"work_id":14976670,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083281,"email":"o***n@hwac.uk","display_order":7340032,"name":"Oliver Lemon","title":"Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation"},{"id":4735473,"work_id":14976670,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":695287,"email":"o***n@inf.ed.ac.uk","display_order":7864320,"name":"Oliver Lemon","title":"Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation"},{"id":4735514,"work_id":14976670,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":114196,"email":"k***a@ict.usc.edu","display_order":8126464,"name":"Kallirroi Georgila","title":"Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation"}],"downloadable_attachments":[{"id":43681463,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681463/thumbnails/1.jpg","file_name":"D6_4-part2.pdf","download_url":"https://www.academia.edu/attachments/43681463/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Final_Report_on_Multimodal_Experiments_P.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681463/D6_4-part2-libre.pdf?1457873737=\u0026response-content-disposition=attachment%3B+filename%3DFinal_Report_on_Multimodal_Experiments_P.pdf\u0026Expires=1732458747\u0026Signature=bJCdTAoEXFHOK7KzsiXT4bLGnUHPlvl86eRpCnjSmCUnvqcm07KXtrFfKaiES-siurPh9gqQXupFcrgNiNd4YMxDtx-iJ4VvvEWXQFluwj0nYEF2UmmXpeHjfQ7AvC7rhdHAvZLH-eNfiiAwK6sy7-xXoZpGz22hB5uScKM5XOSPpGs3rLE4WsJt3RRTy0AASZ-CCDVHplytFfSubC-PvtNu~JgK2hv1ubOyRxC2MdAISnDAhZM5Bas0g1e7q35Qu3iijTq0~flgtSQ2FmYo29~R9smFqBuD1VwH0BxijBJPFMeBBlHUp3uk998D5WWUOJjj4RgWF4Y~iU~MfkSxyA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Final_Report_on_Multimodal_Experiments_Part_II_Experiments_for_data_collection_and_technology_evaluation","translated_slug":"","page_count":66,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681463,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681463/thumbnails/1.jpg","file_name":"D6_4-part2.pdf","download_url":"https://www.academia.edu/attachments/43681463/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Final_Report_on_Multimodal_Experiments_P.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681463/D6_4-part2-libre.pdf?1457873737=\u0026response-content-disposition=attachment%3B+filename%3DFinal_Report_on_Multimodal_Experiments_P.pdf\u0026Expires=1732458747\u0026Signature=bJCdTAoEXFHOK7KzsiXT4bLGnUHPlvl86eRpCnjSmCUnvqcm07KXtrFfKaiES-siurPh9gqQXupFcrgNiNd4YMxDtx-iJ4VvvEWXQFluwj0nYEF2UmmXpeHjfQ7AvC7rhdHAvZLH-eNfiiAwK6sy7-xXoZpGz22hB5uScKM5XOSPpGs3rLE4WsJt3RRTy0AASZ-CCDVHplytFfSubC-PvtNu~JgK2hv1ubOyRxC2MdAISnDAhZM5Bas0g1e7q35Qu3iijTq0~flgtSQ2FmYo29~R9smFqBuD1VwH0BxijBJPFMeBBlHUp3uk998D5WWUOJjj4RgWF4Y~iU~MfkSxyA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":153168,"name":"Data Collection","url":"https://www.academia.edu/Documents/in/Data_Collection"}],"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="14976669"><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/14976669/Incremental_Bayesian_networks_for_structure_prediction"><img alt="Research paper thumbnail of Incremental Bayesian networks for structure prediction" class="work-thumbnail" src="https://attachments.academia-assets.com/43681484/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/14976669/Incremental_Bayesian_networks_for_structure_prediction">Incremental Bayesian networks for structure prediction</a></div><div class="wp-workCard_item"><span>Proceedings of the 24th international conference on Machine learning - ICML '07</span><span>, 2007</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="b22b0db8f7ee2604cd1f3704467d550b" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681484,"asset_id":14976669,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681484/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976669"><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="14976669"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976669; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976669]").text(description); $(".js-view-count[data-work-id=14976669]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976669; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976669']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976669, 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: "b22b0db8f7ee2604cd1f3704467d550b" } } $('.js-work-strip[data-work-id=14976669]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976669,"title":"Incremental Bayesian networks for structure prediction","translated_title":"","metadata":{"grobid_abstract":"We propose a class of graphical models appropriate for structure prediction problems where the model structure is a function of the output structure. Incremental Sigmoid Belief Networks (ISBNs) avoid the need to sum over the possible model structures by using directed arcs and incrementally specifying the model structure. Exact inference in such directed models is not tractable, but we derive two efficient approximations based on mean field methods, which prove effective in artificial experiments. We then demonstrate their effectiveness on a benchmark natural language parsing task, where they achieve state-of-the-art accuracy. Also, the model which is a closer approximation to an ISBN has better parsing accuracy, suggesting that ISBNs are an appropriate abstract model of structure prediction tasks.","publication_date":{"day":null,"month":null,"year":2007,"errors":{}},"publication_name":"Proceedings of the 24th international conference on Machine learning - ICML '07","grobid_abstract_attachment_id":43681484},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976669/Incremental_Bayesian_networks_for_structure_prediction","translated_internal_url":"","created_at":"2015-08-17T02:32:10.712-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735502,"work_id":14976669,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":57191,"email":"t***v@mmci.uni-saarland.de","display_order":0,"name":"Ivan Titov","title":"Incremental Bayesian networks for structure prediction"}],"downloadable_attachments":[{"id":43681484,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681484/thumbnails/1.jpg","file_name":"351.pdf","download_url":"https://www.academia.edu/attachments/43681484/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Incremental_Bayesian_networks_for_struct.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681484/351-libre.pdf?1457873730=\u0026response-content-disposition=attachment%3B+filename%3DIncremental_Bayesian_networks_for_struct.pdf\u0026Expires=1732458747\u0026Signature=b5dOQL~xSLYAjWcpx6-ZKB~euFhB9fK5PB18vVk6ktF0hL7n39bDqdb58o2MLf1d4RJitt~OSNL5NjAoHC4Jmddoof6auy~~VHhPN7NdFI1BcHqElVOBMprfH5cJ1SEFCbDfWUchbF0J2fOZ3Cm6DRl-DDs3kBPMEfxUww4Ldfu8FRRGJJKc2Hslx9iJbD0Hr9tkMYZC4Uljh2rS2eUCE0wfnpV9LYy1cdSht682esBwPGGiQ6k-RJr8hBc1oz7q5byX1Vj8Dk0MlMhVH5IaRs551wz620XfcSZb~4~7Hn7eJbvtcD7w3ze1M7IKZ2eIqRS600ZvVm4LuVtueFP1sw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Incremental_Bayesian_networks_for_structure_prediction","translated_slug":"","page_count":8,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681484,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681484/thumbnails/1.jpg","file_name":"351.pdf","download_url":"https://www.academia.edu/attachments/43681484/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Incremental_Bayesian_networks_for_struct.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681484/351-libre.pdf?1457873730=\u0026response-content-disposition=attachment%3B+filename%3DIncremental_Bayesian_networks_for_struct.pdf\u0026Expires=1732458747\u0026Signature=b5dOQL~xSLYAjWcpx6-ZKB~euFhB9fK5PB18vVk6ktF0hL7n39bDqdb58o2MLf1d4RJitt~OSNL5NjAoHC4Jmddoof6auy~~VHhPN7NdFI1BcHqElVOBMprfH5cJ1SEFCbDfWUchbF0J2fOZ3Cm6DRl-DDs3kBPMEfxUww4Ldfu8FRRGJJKc2Hslx9iJbD0Hr9tkMYZC4Uljh2rS2eUCE0wfnpV9LYy1cdSht682esBwPGGiQ6k-RJr8hBc1oz7q5byX1Vj8Dk0MlMhVH5IaRs551wz620XfcSZb~4~7Hn7eJbvtcD7w3ze1M7IKZ2eIqRS600ZvVm4LuVtueFP1sw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":4600,"name":"Protein Structure Prediction","url":"https://www.academia.edu/Documents/in/Protein_Structure_Prediction"},{"id":274599,"name":"Bayesian Network","url":"https://www.academia.edu/Documents/in/Bayesian_Network"},{"id":315917,"name":"Natural Language Parsing","url":"https://www.academia.edu/Documents/in/Natural_Language_Parsing"},{"id":663297,"name":"Bayesian Belief Network","url":"https://www.academia.edu/Documents/in/Bayesian_Belief_Network"},{"id":886652,"name":"Graphical Model","url":"https://www.academia.edu/Documents/in/Graphical_Model"}],"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="14976668"><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/14976668/Porting_statistical_parsers_with_data_defined_kernels"><img alt="Research paper thumbnail of Porting statistical parsers with data-defined kernels" class="work-thumbnail" src="https://attachments.academia-assets.com/43681661/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/14976668/Porting_statistical_parsers_with_data_defined_kernels">Porting statistical parsers with data-defined kernels</a></div><div class="wp-workCard_item"><span>Proceedings of the Tenth Conference on Computational Natural Language Learning - CoNLL-X '06</span><span>, 2006</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="8d8119239a2def6c35916d7efd143f46" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681661,"asset_id":14976668,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681661/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976668"><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="14976668"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976668; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976668]").text(description); $(".js-view-count[data-work-id=14976668]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976668; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976668']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976668, 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: "8d8119239a2def6c35916d7efd143f46" } } $('.js-work-strip[data-work-id=14976668]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976668,"title":"Porting statistical parsers with data-defined kernels","translated_title":"","metadata":{"grobid_abstract":"Previous results have shown disappointing performance when porting a parser trained on one domain to another domain where only a small amount of data is available. We propose the use of data-defined kernels as a way to exploit statistics from a source domain while still specializing a parser to a target domain. A probabilistic model trained on the source domain (and possibly also the target domain) is used to define a kernel, which is then used in a large margin classifier trained only on the target domain. With a SVM classifier and a neural network probabilistic model, this method achieves improved performance over the probabilistic model alone.","publication_date":{"day":null,"month":null,"year":2006,"errors":{}},"publication_name":"Proceedings of the Tenth Conference on Computational Natural Language Learning - CoNLL-X '06","grobid_abstract_attachment_id":43681661},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976668/Porting_statistical_parsers_with_data_defined_kernels","translated_internal_url":"","created_at":"2015-08-17T02:32:10.591-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735539,"work_id":14976668,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":57191,"email":"t***v@mmci.uni-saarland.de","display_order":0,"name":"Ivan Titov","title":"Porting statistical parsers with data-defined kernels"}],"downloadable_attachments":[{"id":43681661,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681661/thumbnails/1.jpg","file_name":"titov_conll06.pdf","download_url":"https://www.academia.edu/attachments/43681661/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Porting_statistical_parsers_with_data_de.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681661/titov_conll06-libre.pdf?1457873716=\u0026response-content-disposition=attachment%3B+filename%3DPorting_statistical_parsers_with_data_de.pdf\u0026Expires=1732458747\u0026Signature=doTZ8KPP67zUGT2ww2BCigtjBu~k8XxFZUQc0~2saI10pe4EOZ2ZKtoh3WyRy1hQDjRaKvNl3MlC4UMwK6BeO909vj3-TfaZ9MYHsvdC~QFI2eCG1W8ASEtb8J~BSP~cjk3iCI6odNOp~9Xhxeg6OzE6DNowLPq1PUd5XFcZVyUpFKVa7w~41MSRJJeHpO2a5lRb8NN0PdlfCBEWf5sa2AEDzSeBLVMn3BK3L8zOG9hSi0aucGDo190r5Q9zdlbRjTI8Lg90DYrU-JYH6XWSMZ3NaJxpo2ztC~fsRj7gppjbCzh1gn5Z2vzXI0eA5bWGyPX3A5JTsJtuPO-VIuGl~g__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Porting_statistical_parsers_with_data_defined_kernels","translated_slug":"","page_count":8,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681661,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681661/thumbnails/1.jpg","file_name":"titov_conll06.pdf","download_url":"https://www.academia.edu/attachments/43681661/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Porting_statistical_parsers_with_data_de.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681661/titov_conll06-libre.pdf?1457873716=\u0026response-content-disposition=attachment%3B+filename%3DPorting_statistical_parsers_with_data_de.pdf\u0026Expires=1732458747\u0026Signature=doTZ8KPP67zUGT2ww2BCigtjBu~k8XxFZUQc0~2saI10pe4EOZ2ZKtoh3WyRy1hQDjRaKvNl3MlC4UMwK6BeO909vj3-TfaZ9MYHsvdC~QFI2eCG1W8ASEtb8J~BSP~cjk3iCI6odNOp~9Xhxeg6OzE6DNowLPq1PUd5XFcZVyUpFKVa7w~41MSRJJeHpO2a5lRb8NN0PdlfCBEWf5sa2AEDzSeBLVMn3BK3L8zOG9hSi0aucGDo190r5Q9zdlbRjTI8Lg90DYrU-JYH6XWSMZ3NaJxpo2ztC~fsRj7gppjbCzh1gn5Z2vzXI0eA5bWGyPX3A5JTsJtuPO-VIuGl~g__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":26066,"name":"Neural Network","url":"https://www.academia.edu/Documents/in/Neural_Network"},{"id":99531,"name":"Probabilistic Model Checking","url":"https://www.academia.edu/Documents/in/Probabilistic_Model_Checking"}],"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="14976667"><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/14976667/A_Latent_Variable_Model_for_Generative_Dependency_Parsing"><img alt="Research paper thumbnail of A Latent Variable Model for Generative Dependency Parsing" class="work-thumbnail" src="https://attachments.academia-assets.com/43681477/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/14976667/A_Latent_Variable_Model_for_Generative_Dependency_Parsing">A Latent Variable Model for Generative Dependency Parsing</a></div><div class="wp-workCard_item"><span>Text, Speech and Language Technology</span><span>, 2010</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="ab27089df63b41f5649dc629934fd02f" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681477,"asset_id":14976667,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681477/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976667"><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="14976667"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976667; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976667]").text(description); $(".js-view-count[data-work-id=14976667]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976667; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976667']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976667, 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: "ab27089df63b41f5649dc629934fd02f" } } $('.js-work-strip[data-work-id=14976667]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976667,"title":"A Latent Variable Model for Generative Dependency Parsing","translated_title":"","metadata":{"grobid_abstract":"We propose a generative dependency parsing model which uses binary latent variables to induce conditioning features. To define this model we use a recently proposed class of Bayesian Networks for structured prediction, Incremental Sigmoid Belief Networks. We demonstrate that the proposed model achieves state-of-the-art results on three different languages. We also demonstrate that the features induced by the ISBN's latent variables are crucial to this success, and show that the proposed model is particularly good on long dependencies.","publication_date":{"day":null,"month":null,"year":2010,"errors":{}},"publication_name":"Text, Speech and Language Technology","grobid_abstract_attachment_id":43681477},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976667/A_Latent_Variable_Model_for_Generative_Dependency_Parsing","translated_internal_url":"","created_at":"2015-08-17T02:32:10.469-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735493,"work_id":14976667,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":57191,"email":"t***v@mmci.uni-saarland.de","display_order":0,"name":"Ivan Titov","title":"A Latent Variable Model for Generative Dependency Parsing"}],"downloadable_attachments":[{"id":43681477,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681477/thumbnails/1.jpg","file_name":"A_Latent_Variable_Model_for_Generative_D20160313-6151-131tkf4.pdf","download_url":"https://www.academia.edu/attachments/43681477/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"A_Latent_Variable_Model_for_Generative_D.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681477/A_Latent_Variable_Model_for_Generative_D20160313-6151-131tkf4-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DA_Latent_Variable_Model_for_Generative_D.pdf\u0026Expires=1732458747\u0026Signature=HPGJdCTMoyuFAO-CId3PQmtAmdQAD5DyKlXVSm8EshS7hFuBYxWN1V1wBHPjFyybaWFjA5re~GFb3i-mV~jx0XSmoFphiezhfHJ3d-hNkU0kvFH0Jt4O73lSrzfRChmivVV5GLOWH7xtdeXutmvsB9krVI9p6ZW6G-nhDZRic0bBYK0wqHJwYS61MonBtlwff60ZhP2VoX8siAiqglvAAu4RxP8qfXatpmQb-8Xh0d8Wr7E~hIfiBWCdHj2fs7Yl6odfoyklNhJDgPlIYNORKQlVl4RHtTFw-bgjCK-4Ow2U04XiRw3cla89Rl9H9f6gZcCLq-SM5LtnS31cW1GnYA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"A_Latent_Variable_Model_for_Generative_Dependency_Parsing","translated_slug":"","page_count":12,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681477,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681477/thumbnails/1.jpg","file_name":"A_Latent_Variable_Model_for_Generative_D20160313-6151-131tkf4.pdf","download_url":"https://www.academia.edu/attachments/43681477/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"A_Latent_Variable_Model_for_Generative_D.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681477/A_Latent_Variable_Model_for_Generative_D20160313-6151-131tkf4-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DA_Latent_Variable_Model_for_Generative_D.pdf\u0026Expires=1732458747\u0026Signature=HPGJdCTMoyuFAO-CId3PQmtAmdQAD5DyKlXVSm8EshS7hFuBYxWN1V1wBHPjFyybaWFjA5re~GFb3i-mV~jx0XSmoFphiezhfHJ3d-hNkU0kvFH0Jt4O73lSrzfRChmivVV5GLOWH7xtdeXutmvsB9krVI9p6ZW6G-nhDZRic0bBYK0wqHJwYS61MonBtlwff60ZhP2VoX8siAiqglvAAu4RxP8qfXatpmQb-8Xh0d8Wr7E~hIfiBWCdHj2fs7Yl6odfoyklNhJDgPlIYNORKQlVl4RHtTFw-bgjCK-4Ow2U04XiRw3cla89Rl9H9f6gZcCLq-SM5LtnS31cW1GnYA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":286240,"name":"Minimum Spanning Tree","url":"https://www.academia.edu/Documents/in/Minimum_Spanning_Tree"},{"id":297057,"name":"Dependency Parsing","url":"https://www.academia.edu/Documents/in/Dependency_Parsing"}],"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="14976666"><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/14976666/for_Large_Categorization_Problems"><img alt="Research paper thumbnail of for Large Categorization Problems" 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/14976666/for_Large_Categorization_Problems">for Large Categorization Problems</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">In multi-class categorization problems with a very large or unbounded number of classes, it is of...</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">In multi-class categorization problems with a very large or unbounded number of classes, it is often not compu- tationally feasible to train and/or test a kernel-based classifier. One solution is to use a fast computation to pre-select a subset of the classes for reranking with a kernel method, but even then tractability can be a problem. We investigate using trained</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="14976666"><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="14976666"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976666; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976666]").text(description); $(".js-view-count[data-work-id=14976666]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976666; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976666']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976666, 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" } } $('.js-work-strip[data-work-id=14976666]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976666,"title":"for Large Categorization Problems","translated_title":"","metadata":{"abstract":"In multi-class categorization problems with a very large or unbounded number of classes, it is often not compu- tationally feasible to train and/or test a kernel-based classifier. One solution is to use a fast computation to pre-select a subset of the classes for reranking with a kernel method, but even then tractability can be a problem. We investigate using trained","publication_date":{"day":null,"month":null,"year":2000,"errors":{}}},"translated_abstract":"In multi-class categorization problems with a very large or unbounded number of classes, it is often not compu- tationally feasible to train and/or test a kernel-based classifier. One solution is to use a fast computation to pre-select a subset of the classes for reranking with a kernel method, but even then tractability can be a problem. We investigate using trained","internal_url":"https://www.academia.edu/14976666/for_Large_Categorization_Problems","translated_internal_url":"","created_at":"2015-08-17T02:32:10.285-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735503,"work_id":14976666,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":57191,"email":"t***v@mmci.uni-saarland.de","display_order":0,"name":"Ivan Titov","title":"for Large Categorization Problems"}],"downloadable_attachments":[],"slug":"for_Large_Categorization_Problems","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[{"id":26066,"name":"Neural Network","url":"https://www.academia.edu/Documents/in/Neural_Network"},{"id":194045,"name":"Multi-layer Perceptron","url":"https://www.academia.edu/Documents/in/Multi-layer_Perceptron"},{"id":315917,"name":"Natural Language Parsing","url":"https://www.academia.edu/Documents/in/Natural_Language_Parsing"},{"id":1837730,"name":"Neural Network Model","url":"https://www.academia.edu/Documents/in/Neural_Network_Model"}],"urls":[{"id":5217564,"url":"http://homepages.inf.ed.ac.uk/jhender6/papers/titov_ijcnn05.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="14976664"><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/14976664/Data_defined_kernels_for_parse_reranking_derived_from_probabilistic_models"><img alt="Research paper thumbnail of Data-defined kernels for parse reranking derived from probabilistic models" class="work-thumbnail" src="https://attachments.academia-assets.com/43681471/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/14976664/Data_defined_kernels_for_parse_reranking_derived_from_probabilistic_models">Data-defined kernels for parse reranking derived from probabilistic models</a></div><div class="wp-workCard_item"><span>Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05</span><span>, 2005</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="9c3b6394f8c711154596a9c1ed31f4ac" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681471,"asset_id":14976664,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681471/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976664"><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="14976664"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976664; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976664]").text(description); $(".js-view-count[data-work-id=14976664]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976664; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976664']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976664, 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: "9c3b6394f8c711154596a9c1ed31f4ac" } } $('.js-work-strip[data-work-id=14976664]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976664,"title":"Data-defined kernels for parse reranking derived from probabilistic models","translated_title":"","metadata":{"grobid_abstract":"Previous research applying kernel methods to natural language parsing have focussed on proposing kernels over parse trees, which are hand-crafted based on domain knowledge and computational considerations. In this paper we propose a method for defining kernels in terms of a probabilistic model of parsing. This model is then trained, so that the parameters of the probabilistic model reflect the generalizations in the training data. The method we propose then uses these trained parameters to define a kernel for reranking parse trees. In experiments, we use a neural network based statistical parser as the probabilistic model, and use the resulting kernel with the Voted Perceptron algorithm to rerank the top 20 parses from the probabilistic model. This method achieves a significant improvement over the accuracy of the probabilistic model.","publication_date":{"day":null,"month":null,"year":2005,"errors":{}},"publication_name":"Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05","grobid_abstract_attachment_id":43681471},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976664/Data_defined_kernels_for_parse_reranking_derived_from_probabilistic_models","translated_internal_url":"","created_at":"2015-08-17T02:32:09.222-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735492,"work_id":14976664,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":57191,"email":"t***v@mmci.uni-saarland.de","display_order":0,"name":"Ivan Titov","title":"Data-defined kernels for parse reranking derived from probabilistic models"}],"downloadable_attachments":[{"id":43681471,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681471/thumbnails/1.jpg","file_name":"P05-1023.pdf","download_url":"https://www.academia.edu/attachments/43681471/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Data_defined_kernels_for_parse_reranking.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681471/P05-1023-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DData_defined_kernels_for_parse_reranking.pdf\u0026Expires=1732458747\u0026Signature=ayVvecc9OLYV6avi3aIv1Ztye-eLzp4CmbX5aHKNdESA296WhBvTolro3zN0OcV1Ve-dmnSih5jKcDIjF6KfR-1E438wMAtJatXpI2uYXbqp717-HKkL02Key7Je2U2IaiBHs67fePacrD7Jtw2NJfyneNoQ-zNHVhWb85f2pnZbRzkLYAIjj78YrhJZAt0WFaaFr2TS57cPir2Ai8KQUu1nESyGvTMffnxXiNZXC3leIT-EPpg5G9MnZvl9OeY9Pn8ygYijPErFgvTclSsUslE190ayhmdot~~hajcQw7viqj-mLLPME94oBTTkgbUVwWbgC0sOAmbgqtsXPY4OcQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Data_defined_kernels_for_parse_reranking_derived_from_probabilistic_models","translated_slug":"","page_count":8,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681471,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681471/thumbnails/1.jpg","file_name":"P05-1023.pdf","download_url":"https://www.academia.edu/attachments/43681471/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Data_defined_kernels_for_parse_reranking.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681471/P05-1023-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DData_defined_kernels_for_parse_reranking.pdf\u0026Expires=1732458747\u0026Signature=ayVvecc9OLYV6avi3aIv1Ztye-eLzp4CmbX5aHKNdESA296WhBvTolro3zN0OcV1Ve-dmnSih5jKcDIjF6KfR-1E438wMAtJatXpI2uYXbqp717-HKkL02Key7Je2U2IaiBHs67fePacrD7Jtw2NJfyneNoQ-zNHVhWb85f2pnZbRzkLYAIjj78YrhJZAt0WFaaFr2TS57cPir2Ai8KQUu1nESyGvTMffnxXiNZXC3leIT-EPpg5G9MnZvl9OeY9Pn8ygYijPErFgvTclSsUslE190ayhmdot~~hajcQw7viqj-mLLPME94oBTTkgbUVwWbgC0sOAmbgqtsXPY4OcQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":26066,"name":"Neural Network","url":"https://www.academia.edu/Documents/in/Neural_Network"},{"id":99531,"name":"Probabilistic Model Checking","url":"https://www.academia.edu/Documents/in/Probabilistic_Model_Checking"},{"id":315917,"name":"Natural Language Parsing","url":"https://www.academia.edu/Documents/in/Natural_Language_Parsing"}],"urls":[]}, 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="3393443" id="papers"><div class="js-work-strip profile--work_container" data-work-id="14976685"><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/14976685/Domain_Adaptation_with_Artificial_Data_for_Semantic_Parsing_of_Speech"><img alt="Research paper thumbnail of Domain Adaptation with Artificial Data for Semantic Parsing of Speech" class="work-thumbnail" src="https://attachments.academia-assets.com/43681468/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/14976685/Domain_Adaptation_with_Artificial_Data_for_Semantic_Parsing_of_Speech">Domain Adaptation with Artificial Data for Semantic Parsing of Speech</a></div><div class="wp-workCard_item"><span>North American Chapter of the Association for Computational Linguistics</span><span>, 2009</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">We adapt a semantic role parser to the do- main of goal-directed speech by creating an artificial...</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">We adapt a semantic role parser to the do- main of goal-directed speech by creating an artificial treebank from an existing text tree- bank. We use a three-component model that includes distributional models from both tar- get and source domains. We show that we im- prove the parser&#39;s performance on utterances collected from human-machine dialogues by training on the artificially</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="ece22554900c773114d33c55824c1d54" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681468,"asset_id":14976685,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681468/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&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="14976685"><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="14976685"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976685; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976685]").text(description); $(".js-view-count[data-work-id=14976685]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976685; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976685']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976685, 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: "ece22554900c773114d33c55824c1d54" } } $('.js-work-strip[data-work-id=14976685]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976685,"title":"Domain Adaptation with Artificial Data for Semantic Parsing of Speech","translated_title":"","metadata":{"abstract":"We adapt a semantic role parser to the do- main of goal-directed speech by creating an artificial treebank from an existing text tree- bank. We use a three-component model that includes distributional models from both tar- get and source domains. We show that we im- prove the parser\u0026#39;s performance on utterances collected from human-machine dialogues by training on the artificially","publication_date":{"day":null,"month":null,"year":2009,"errors":{}},"publication_name":"North American Chapter of the Association for Computational Linguistics"},"translated_abstract":"We adapt a semantic role parser to the do- main of goal-directed speech by creating an artificial treebank from an existing text tree- bank. We use a three-component model that includes distributional models from both tar- get and source domains. We show that we im- prove the parser\u0026#39;s performance on utterances collected from human-machine dialogues by training on the artificially","internal_url":"https://www.academia.edu/14976685/Domain_Adaptation_with_Artificial_Data_for_Semantic_Parsing_of_Speech","translated_internal_url":"","created_at":"2015-08-17T02:32:12.629-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735287,"work_id":14976685,"tagging_user_id":33971246,"tagged_user_id":26057544,"co_author_invite_id":null,"email":"p***1@gmail.com","affiliation":"Universit茅 de Gen猫ve","display_order":0,"name":"Paola Merlo","title":"Domain Adaptation with Artificial Data for Semantic Parsing of Speech"},{"id":4735300,"work_id":14976685,"tagging_user_id":33971246,"tagged_user_id":24919989,"co_author_invite_id":null,"email":"p***o@unige.ch","affiliation":"Universit茅 de Gen猫ve","display_order":4194304,"name":"paola merlo","title":"Domain Adaptation with Artificial Data for Semantic Parsing of Speech"},{"id":4735314,"work_id":14976685,"tagging_user_id":33971246,"tagged_user_id":9598512,"co_author_invite_id":null,"email":"p***b@gmail.com","display_order":6291456,"name":"Paola Merlo","title":"Domain Adaptation with Artificial Data for Semantic Parsing of Speech"},{"id":4735490,"work_id":14976685,"tagging_user_id":33971246,"tagged_user_id":4893055,"co_author_invite_id":null,"email":"l***s@gmail.com","affiliation":"University of Malta","display_order":7340032,"name":"Lonneke van der Plas","title":"Domain Adaptation with Artificial Data for Semantic Parsing of Speech"},{"id":4735520,"work_id":14976685,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1070304,"email":"l***s@unige.ch","display_order":7864320,"name":"L. Van Der Plas","title":"Domain Adaptation with Artificial Data for Semantic Parsing of Speech"}],"downloadable_attachments":[{"id":43681468,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681468/thumbnails/1.jpg","file_name":"N09-2032.pdf","download_url":"https://www.academia.edu/attachments/43681468/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Domain_Adaptation_with_Artificial_Data_f.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681468/N09-2032-libre.pdf?1457873730=\u0026response-content-disposition=attachment%3B+filename%3DDomain_Adaptation_with_Artificial_Data_f.pdf\u0026Expires=1732458746\u0026Signature=I~kcqlimnVf-hROaqRKW7rP88mfXGj5t7aV3bGCmTItNDb8s4ZtuQ9ESvg8XsHCATqZCMtp0VOpCQipieg-I7mhbT2dEZrxcDTrE6RRb2~-x3MLYSxMLkY2QLQw0-LHmxfrt8Xww2~LBn-J8TxG2qUVPWQS5QDQoimHwyqS5q-Pw81NTo2AQfTyd4ne1QLykxMefJqroUToiK4TC-TBSiNS6TFt5XgL1ppi5zsez4vOEdeA8jJYfLPXralyv4H3H4k-kisLJyTwVO0wDXVO7gXrHz7X4tegfjcuDoU~2id6j6YGSXWmYmswaLrsfuOPvSnY61BGshRwFLbULDRcDJA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Domain_Adaptation_with_Artificial_Data_for_Semantic_Parsing_of_Speech","translated_slug":"","page_count":4,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681468,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681468/thumbnails/1.jpg","file_name":"N09-2032.pdf","download_url":"https://www.academia.edu/attachments/43681468/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Domain_Adaptation_with_Artificial_Data_f.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681468/N09-2032-libre.pdf?1457873730=\u0026response-content-disposition=attachment%3B+filename%3DDomain_Adaptation_with_Artificial_Data_f.pdf\u0026Expires=1732458746\u0026Signature=I~kcqlimnVf-hROaqRKW7rP88mfXGj5t7aV3bGCmTItNDb8s4ZtuQ9ESvg8XsHCATqZCMtp0VOpCQipieg-I7mhbT2dEZrxcDTrE6RRb2~-x3MLYSxMLkY2QLQw0-LHmxfrt8Xww2~LBn-J8TxG2qUVPWQS5QDQoimHwyqS5q-Pw81NTo2AQfTyd4ne1QLykxMefJqroUToiK4TC-TBSiNS6TFt5XgL1ppi5zsez4vOEdeA8jJYfLPXralyv4H3H4k-kisLJyTwVO0wDXVO7gXrHz7X4tegfjcuDoU~2id6j6YGSXWmYmswaLrsfuOPvSnY61BGshRwFLbULDRcDJA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":2007534,"name":"Component Model","url":"https://www.academia.edu/Documents/in/Component_Model"}],"urls":[{"id":5217570,"url":"http://www.informatik.uni-trier.de/~ley/db/conf/naacl/naacl2009s.html#PlasHM09"}]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="14976684"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/14976684/Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning"><img alt="Research paper thumbnail of Undirected Machine Translation with Discriminative Reinforcement Learning" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/14976684/Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning">Undirected Machine Translation with Discriminative Reinforcement Learning</a></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="14976684"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="14976684"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976684; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976684]").text(description); $(".js-view-count[data-work-id=14976684]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976684; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976684']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976684, 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" } } $('.js-work-strip[data-work-id=14976684]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976684,"title":"Undirected Machine Translation with Discriminative Reinforcement Learning","translated_title":"","metadata":{},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976684/Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning","translated_internal_url":"","created_at":"2015-08-17T02:32:12.504-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735410,"work_id":14976684,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083276,"email":"a***o@unige.ch","display_order":0,"name":"Andrea Gesmundo","title":"Undirected Machine Translation with Discriminative Reinforcement Learning"}],"downloadable_attachments":[],"slug":"Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[],"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="14976683"><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/14976683/Incremental_Sigmoid_Belief_Networks_for_Grammar_Learning"><img alt="Research paper thumbnail of Incremental Sigmoid Belief Networks for Grammar Learning" class="work-thumbnail" src="https://attachments.academia-assets.com/43681505/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/14976683/Incremental_Sigmoid_Belief_Networks_for_Grammar_Learning">Incremental Sigmoid Belief Networks for Grammar Learning</a></div><div class="wp-workCard_item"><span>Journal of Machine Learning Research</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">We propose a class of Bayesian networks appropriate for structured prediction problems where the ...</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">We propose a class of Bayesian networks appropriate for structured prediction problems where the Bayesian network&#39;s model structure is a function of the predicted output structure. These incremental sigmoid belief networks (ISBNs) make decoding possible because inference with partial output structures does not require summing over the unboundedly many compatible model structures, due to their directed edges and incrementally specified model structure. ISBNs are specifically targeted at challenging structured prediction problems such as natural language parsing, where learning the domain&#39;s complex statistical dependencies benefits from large numbers of latent variables. While exact inference in ISBNs with large numbers of latent variables is not tractable, we propose two efficient approximations. First, we demonstrate that a previous neural network parsing model can be viewed as a coarse mean-field approximation to inference with ISBNs. We then derive a more accurate but stil...</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="cd274b1f806da461315f75203a06caa8" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681505,"asset_id":14976683,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681505/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&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="14976683"><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="14976683"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976683; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976683]").text(description); $(".js-view-count[data-work-id=14976683]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976683; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976683']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976683, 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: "cd274b1f806da461315f75203a06caa8" } } $('.js-work-strip[data-work-id=14976683]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976683,"title":"Incremental Sigmoid Belief Networks for Grammar Learning","translated_title":"","metadata":{"abstract":"We propose a class of Bayesian networks appropriate for structured prediction problems where the Bayesian network\u0026#39;s model structure is a function of the predicted output structure. These incremental sigmoid belief networks (ISBNs) make decoding possible because inference with partial output structures does not require summing over the unboundedly many compatible model structures, due to their directed edges and incrementally specified model structure. ISBNs are specifically targeted at challenging structured prediction problems such as natural language parsing, where learning the domain\u0026#39;s complex statistical dependencies benefits from large numbers of latent variables. While exact inference in ISBNs with large numbers of latent variables is not tractable, we propose two efficient approximations. First, we demonstrate that a previous neural network parsing model can be viewed as a coarse mean-field approximation to inference with ISBNs. We then derive a more accurate but stil...","publication_name":"Journal of Machine Learning Research"},"translated_abstract":"We propose a class of Bayesian networks appropriate for structured prediction problems where the Bayesian network\u0026#39;s model structure is a function of the predicted output structure. These incremental sigmoid belief networks (ISBNs) make decoding possible because inference with partial output structures does not require summing over the unboundedly many compatible model structures, due to their directed edges and incrementally specified model structure. ISBNs are specifically targeted at challenging structured prediction problems such as natural language parsing, where learning the domain\u0026#39;s complex statistical dependencies benefits from large numbers of latent variables. While exact inference in ISBNs with large numbers of latent variables is not tractable, we propose two efficient approximations. First, we demonstrate that a previous neural network parsing model can be viewed as a coarse mean-field approximation to inference with ISBNs. We then derive a more accurate but stil...","internal_url":"https://www.academia.edu/14976683/Incremental_Sigmoid_Belief_Networks_for_Grammar_Learning","translated_internal_url":"","created_at":"2015-08-17T02:32:12.273-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735504,"work_id":14976683,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":57191,"email":"t***v@mmci.uni-saarland.de","display_order":0,"name":"Ivan Titov","title":"Incremental Sigmoid Belief Networks for Grammar Learning"}],"downloadable_attachments":[{"id":43681505,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681505/thumbnails/1.jpg","file_name":"Incremental_Sigmoid_Belief_Networks_for_20160313-14997-5xzmq2.pdf","download_url":"https://www.academia.edu/attachments/43681505/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Incremental_Sigmoid_Belief_Networks_for.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681505/Incremental_Sigmoid_Belief_Networks_for_20160313-14997-5xzmq2-libre.pdf?1457873730=\u0026response-content-disposition=attachment%3B+filename%3DIncremental_Sigmoid_Belief_Networks_for.pdf\u0026Expires=1732458746\u0026Signature=TrPn15fn8-gjgyccT21efuGQWRgtnpClqvrbJHqjCYy44qu3iNFt1KJ~5xAj4W3Tpl3vvL65H-9H1oDQTvhGZf7GWiye-IYnk5IGOthqrTc6Vs2NA1OkbiK1urvysWWMsBw0qpmjloj--koLhSPlshdmAXkd11VeR0YJCmL51nOQw4Yr3414RvbT-dxj4Eu0R9FPeWOeHEQ5DQp8Pts~5zw~4qoWVnX7O8BMZCDUlPyhkACf1RC3K6JMNBjnDCxtWZuV3umydMEFOLQtm9KfwOJ66uidbb8FHicZ1IeqQcq3ShusohaAYpeYrVSJEQQWqfSE7dolgJBBnzHIB~iIXg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Incremental_Sigmoid_Belief_Networks_for_Grammar_Learning","translated_slug":"","page_count":30,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681505,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681505/thumbnails/1.jpg","file_name":"Incremental_Sigmoid_Belief_Networks_for_20160313-14997-5xzmq2.pdf","download_url":"https://www.academia.edu/attachments/43681505/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Incremental_Sigmoid_Belief_Networks_for.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681505/Incremental_Sigmoid_Belief_Networks_for_20160313-14997-5xzmq2-libre.pdf?1457873730=\u0026response-content-disposition=attachment%3B+filename%3DIncremental_Sigmoid_Belief_Networks_for.pdf\u0026Expires=1732458746\u0026Signature=TrPn15fn8-gjgyccT21efuGQWRgtnpClqvrbJHqjCYy44qu3iNFt1KJ~5xAj4W3Tpl3vvL65H-9H1oDQTvhGZf7GWiye-IYnk5IGOthqrTc6Vs2NA1OkbiK1urvysWWMsBw0qpmjloj--koLhSPlshdmAXkd11VeR0YJCmL51nOQw4Yr3414RvbT-dxj4Eu0R9FPeWOeHEQ5DQp8Pts~5zw~4qoWVnX7O8BMZCDUlPyhkACf1RC3K6JMNBjnDCxtWZuV3umydMEFOLQtm9KfwOJ66uidbb8FHicZ1IeqQcq3ShusohaAYpeYrVSJEQQWqfSE7dolgJBBnzHIB~iIXg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":2008,"name":"Machine Learning","url":"https://www.academia.edu/Documents/in/Machine_Learning"},{"id":663297,"name":"Bayesian Belief Network","url":"https://www.academia.edu/Documents/in/Bayesian_Belief_Network"}],"urls":[{"id":6897528,"url":"https://www.researchgate.net/profile/James_Henderson8/publication/220320210_Incremental_Sigmoid_Belief_Networks_for_Grammar_Learning/links/0deec518b7f3e68091000000.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="14976682"><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/14976682/Temporal_Restricted_Boltzmann_Machines_for_Dependency_Parsing"><img alt="Research paper thumbnail of Temporal Restricted Boltzmann Machines for Dependency Parsing" class="work-thumbnail" src="https://attachments.academia-assets.com/43681521/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/14976682/Temporal_Restricted_Boltzmann_Machines_for_Dependency_Parsing">Temporal Restricted Boltzmann Machines for Dependency Parsing</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">We propose a generative model based on Temporal Restricted Boltzmann Machines for transition base...</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">We propose a generative model based on Temporal Restricted Boltzmann Machines for transition based dependency parsing. The parse tree is built incrementally using a shift-reduce parse and an RBM is used to model each decision step. The RBM at the current time step induces latent features with the help of temporal connections to the relevant previous steps which provide context information. Our parser achieves labeled and unlabeled attachment scores of 88.72% and 91.65% respectively, which compare well with similar previous models and the state-of-the-art.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="b5ba62afb30c37bedd1e533e3ec68fa9" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681521,"asset_id":14976682,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681521/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&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="14976682"><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="14976682"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976682; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976682]").text(description); $(".js-view-count[data-work-id=14976682]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976682; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976682']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976682, 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: "b5ba62afb30c37bedd1e533e3ec68fa9" } } $('.js-work-strip[data-work-id=14976682]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976682,"title":"Temporal Restricted Boltzmann Machines for Dependency Parsing","translated_title":"","metadata":{"abstract":"We propose a generative model based on Temporal Restricted Boltzmann Machines for transition based dependency parsing. The parse tree is built incrementally using a shift-reduce parse and an RBM is used to model each decision step. The RBM at the current time step induces latent features with the help of temporal connections to the relevant previous steps which provide context information. Our parser achieves labeled and unlabeled attachment scores of 88.72% and 91.65% respectively, which compare well with similar previous models and the state-of-the-art."},"translated_abstract":"We propose a generative model based on Temporal Restricted Boltzmann Machines for transition based dependency parsing. The parse tree is built incrementally using a shift-reduce parse and an RBM is used to model each decision step. The RBM at the current time step induces latent features with the help of temporal connections to the relevant previous steps which provide context information. Our parser achieves labeled and unlabeled attachment scores of 88.72% and 91.65% respectively, which compare well with similar previous models and the state-of-the-art.","internal_url":"https://www.academia.edu/14976682/Temporal_Restricted_Boltzmann_Machines_for_Dependency_Parsing","translated_internal_url":"","created_at":"2015-08-17T02:32:12.078-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735524,"work_id":14976682,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083285,"email":"n***g@unige.ch","display_order":0,"name":"N. Garg","title":"Temporal Restricted Boltzmann Machines for Dependency Parsing"}],"downloadable_attachments":[{"id":43681521,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681521/thumbnails/1.jpg","file_name":"Temporal_Restricted_Boltzmann_Machines_f20160313-2737-14s3nuu.pdf","download_url":"https://www.academia.edu/attachments/43681521/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Temporal_Restricted_Boltzmann_Machines_f.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681521/Temporal_Restricted_Boltzmann_Machines_f20160313-2737-14s3nuu-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DTemporal_Restricted_Boltzmann_Machines_f.pdf\u0026Expires=1732458746\u0026Signature=LeQ42vlMpQHYdz4-8WWKMy9~-8eCa3FN6jaK48MMIZe1YaFkf7zLTlmTTqlcYD2Bh6B1A87Kh00s8CFyeU58fgfX0vAMa-MkF53mBXQ42AOWAsA5pDaYqzEdG4BIFaWRzcTI-Bbj326GveGbkTYJfN~lFt0wJX7h7d2DHNADiaavDjpS~pMaR5PEepsOq7TKRscVMXRd8D6s5k3OrrACYkGrgLG7UrcWxzezb2iCBCpQTV-w9OTKwu96K-pTrJ4KGcM6r1i8hdbWRrBE1lrcKExntONYsNlItSHnmmCln8i7HY3UJvXmVr8gU1Qx0ObnhhgqGm3PJ2nt2VbSz2QbIg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Temporal_Restricted_Boltzmann_Machines_for_Dependency_Parsing","translated_slug":"","page_count":55,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681521,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681521/thumbnails/1.jpg","file_name":"Temporal_Restricted_Boltzmann_Machines_f20160313-2737-14s3nuu.pdf","download_url":"https://www.academia.edu/attachments/43681521/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Temporal_Restricted_Boltzmann_Machines_f.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681521/Temporal_Restricted_Boltzmann_Machines_f20160313-2737-14s3nuu-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DTemporal_Restricted_Boltzmann_Machines_f.pdf\u0026Expires=1732458746\u0026Signature=LeQ42vlMpQHYdz4-8WWKMy9~-8eCa3FN6jaK48MMIZe1YaFkf7zLTlmTTqlcYD2Bh6B1A87Kh00s8CFyeU58fgfX0vAMa-MkF53mBXQ42AOWAsA5pDaYqzEdG4BIFaWRzcTI-Bbj326GveGbkTYJfN~lFt0wJX7h7d2DHNADiaavDjpS~pMaR5PEepsOq7TKRscVMXRd8D6s5k3OrrACYkGrgLG7UrcWxzezb2iCBCpQTV-w9OTKwu96K-pTrJ4KGcM6r1i8hdbWRrBE1lrcKExntONYsNlItSHnmmCln8i7HY3UJvXmVr8gU1Qx0ObnhhgqGm3PJ2nt2VbSz2QbIg__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":2008,"name":"Machine Learning","url":"https://www.academia.edu/Documents/in/Machine_Learning"},{"id":322355,"name":"RBM","url":"https://www.academia.edu/Documents/in/RBM"}],"urls":[{"id":6897530,"url":"https://www.researchgate.net/profile/James_Henderson8/publication/220874210_Temporal_Restricted_Boltzmann_Machines_for_Dependency_Parsing/links/551aec310cf2bb7540786dbc.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="14976681"><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/14976681/Scaling_up_Automatic_Cross_Lingual_Semantic_Role_Annotation"><img alt="Research paper thumbnail of Scaling up Automatic Cross-Lingual Semantic Role Annotation" class="work-thumbnail" src="https://attachments.academia-assets.com/43681467/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/14976681/Scaling_up_Automatic_Cross_Lingual_Semantic_Role_Annotation">Scaling up Automatic Cross-Lingual Semantic Role Annotation</a></div><div class="wp-workCard_item wp-workCard--coauthors"><span>by </span><span><a class="" data-click-track="profile-work-strip-authors" href="https://independent.academia.edu/JamesHenderson28">James Henderson</a> and <a class="" data-click-track="profile-work-strip-authors" href="https://unige.academia.edu/paolamerlo">paola merlo</a></span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Broad-coverage semantic annotations for training statistical learners are only available for a ha...</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">Broad-coverage semantic annotations for training statistical learners are only available for a handful of languages. Previous approaches to cross-lingual transfer of semantic annotations have addressed this problem with encouraging results on a small scale. In this paper, we scale up previous efforts by using an automatic approach to semantic annotation that does not rely on a semantic ontology for the target language. Moreover, we improve the quality of the transferred semantic annotations by using a joint syntactic-semantic parser that learns the correlations between syntax and semantics of the target language and smooths out the errors from automatic transfer. We reach a labelled F-measure for predicates and arguments of only 4% and 9% points, respectively, lower than the upper bound from manual annotations.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="be07c39a564b093bd62c1283399962d2" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681467,"asset_id":14976681,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681467/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&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="14976681"><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="14976681"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976681; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976681]").text(description); $(".js-view-count[data-work-id=14976681]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976681; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976681']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976681, 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: "be07c39a564b093bd62c1283399962d2" } } $('.js-work-strip[data-work-id=14976681]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976681,"title":"Scaling up Automatic Cross-Lingual Semantic Role Annotation","translated_title":"","metadata":{"abstract":"Broad-coverage semantic annotations for training statistical learners are only available for a handful of languages. Previous approaches to cross-lingual transfer of semantic annotations have addressed this problem with encouraging results on a small scale. In this paper, we scale up previous efforts by using an automatic approach to semantic annotation that does not rely on a semantic ontology for the target language. Moreover, we improve the quality of the transferred semantic annotations by using a joint syntactic-semantic parser that learns the correlations between syntax and semantics of the target language and smooths out the errors from automatic transfer. We reach a labelled F-measure for predicates and arguments of only 4% and 9% points, respectively, lower than the upper bound from manual annotations."},"translated_abstract":"Broad-coverage semantic annotations for training statistical learners are only available for a handful of languages. Previous approaches to cross-lingual transfer of semantic annotations have addressed this problem with encouraging results on a small scale. In this paper, we scale up previous efforts by using an automatic approach to semantic annotation that does not rely on a semantic ontology for the target language. Moreover, we improve the quality of the transferred semantic annotations by using a joint syntactic-semantic parser that learns the correlations between syntax and semantics of the target language and smooths out the errors from automatic transfer. We reach a labelled F-measure for predicates and arguments of only 4% and 9% points, respectively, lower than the upper bound from manual annotations.","internal_url":"https://www.academia.edu/14976681/Scaling_up_Automatic_Cross_Lingual_Semantic_Role_Annotation","translated_internal_url":"","created_at":"2015-08-17T02:32:11.872-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735288,"work_id":14976681,"tagging_user_id":33971246,"tagged_user_id":26057544,"co_author_invite_id":null,"email":"p***1@gmail.com","affiliation":"Universit茅 de Gen猫ve","display_order":0,"name":"Paola Merlo","title":"Scaling up Automatic Cross-Lingual Semantic Role Annotation"},{"id":4735301,"work_id":14976681,"tagging_user_id":33971246,"tagged_user_id":24919989,"co_author_invite_id":null,"email":"p***o@unige.ch","affiliation":"Universit茅 de Gen猫ve","display_order":4194304,"name":"paola merlo","title":"Scaling up Automatic Cross-Lingual Semantic Role Annotation"},{"id":4735315,"work_id":14976681,"tagging_user_id":33971246,"tagged_user_id":9598512,"co_author_invite_id":null,"email":"p***b@gmail.com","display_order":6291456,"name":"Paola Merlo","title":"Scaling up Automatic Cross-Lingual Semantic Role Annotation"},{"id":4735491,"work_id":14976681,"tagging_user_id":33971246,"tagged_user_id":4893055,"co_author_invite_id":null,"email":"l***s@gmail.com","affiliation":"University of Malta","display_order":7340032,"name":"Lonneke van der Plas","title":"Scaling up Automatic Cross-Lingual Semantic Role Annotation"},{"id":4735521,"work_id":14976681,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1070304,"email":"l***s@unige.ch","display_order":7864320,"name":"L. Van Der Plas","title":"Scaling up Automatic Cross-Lingual Semantic Role Annotation"}],"downloadable_attachments":[{"id":43681467,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681467/thumbnails/1.jpg","file_name":"Scaling_up_Automatic_Cross-Lingual_Seman20160313-2737-1kfcljb.pdf","download_url":"https://www.academia.edu/attachments/43681467/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Scaling_up_Automatic_Cross_Lingual_Seman.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681467/Scaling_up_Automatic_Cross-Lingual_Seman20160313-2737-1kfcljb-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DScaling_up_Automatic_Cross_Lingual_Seman.pdf\u0026Expires=1732458746\u0026Signature=CCZV0OuRXfYEOagnE-qNf4XhdSuDQlp6Jm3~e-wBvGFLBPpADZVGrtCG4cib2M5ZGkr8vX3mC60N6Xh-YvuS6AON4~W2ZPNe7a8TODuKCJcWwFAuTGk~YZa08~oEqdmu~pThv13wD80iNl9PJxUAjs6uUoRSeTa383wH4JfNmE4I6HdCQJ1n86aUWNGWy5ObqplEHsN6l9MR-uSwxXVJKv7Jc-I9WGJyL217lhgLXbdXSwDAsG4uErrc8-6ZByEOYFG5WpiveqVqZcQyx9oJ-HQBo3wlSBEsFbg8gPwcqA9SWLnsRjU~Lq7DAXYVnG7GBdgWKnvX~v8fVwSGyo785g__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Scaling_up_Automatic_Cross_Lingual_Semantic_Role_Annotation","translated_slug":"","page_count":6,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681467,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681467/thumbnails/1.jpg","file_name":"Scaling_up_Automatic_Cross-Lingual_Seman20160313-2737-1kfcljb.pdf","download_url":"https://www.academia.edu/attachments/43681467/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Scaling_up_Automatic_Cross_Lingual_Seman.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681467/Scaling_up_Automatic_Cross-Lingual_Seman20160313-2737-1kfcljb-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DScaling_up_Automatic_Cross_Lingual_Seman.pdf\u0026Expires=1732458746\u0026Signature=CCZV0OuRXfYEOagnE-qNf4XhdSuDQlp6Jm3~e-wBvGFLBPpADZVGrtCG4cib2M5ZGkr8vX3mC60N6Xh-YvuS6AON4~W2ZPNe7a8TODuKCJcWwFAuTGk~YZa08~oEqdmu~pThv13wD80iNl9PJxUAjs6uUoRSeTa383wH4JfNmE4I6HdCQJ1n86aUWNGWy5ObqplEHsN6l9MR-uSwxXVJKv7Jc-I9WGJyL217lhgLXbdXSwDAsG4uErrc8-6ZByEOYFG5WpiveqVqZcQyx9oJ-HQBo3wlSBEsFbg8gPwcqA9SWLnsRjU~Lq7DAXYVnG7GBdgWKnvX~v8fVwSGyo785g__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[],"urls":[{"id":6897525,"url":"https://www.researchgate.net/profile/James_Henderson8/publication/220874897_Scaling_up_Automatic_Cross-Lingual_Semantic_Role_Annotation/links/0deec518b7f39257e3000000.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="14976679"><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/14976679/Heuristic_Search_for_Non_Bottom_Up_Tree_Structure_Prediction"><img alt="Research paper thumbnail of Heuristic Search for Non-Bottom-Up Tree Structure Prediction" class="work-thumbnail" src="https://attachments.academia-assets.com/43681509/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/14976679/Heuristic_Search_for_Non_Bottom_Up_Tree_Structure_Prediction">Heuristic Search for Non-Bottom-Up Tree Structure Prediction</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">State of the art Tree Structures Prediction techniques rely on bottom-up decoding. These approach...</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 Tree Structures Prediction techniques rely on bottom-up decoding. These approaches allow the use of context-free features and bottom-up features. We discuss the limitations of mainstream techniques in solving common Natural Language Processing tasks. Then we devise a new framework that goes beyond Bottom-up Decoding, and that allows a better integration of contextual features. Furthermore we design a system that addresses these issues and we test it on Hierarchical Machine Translation, a well known tree structure prediction problem. The structure of the proposed system allows the incorporation of non-bottom-up features and relies on a more sophisticated decoding approach. We show that the proposed approach can find better translations using a smaller portion of the search space.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="abb1b7b69f8112dc0f3a3608323254d4" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681509,"asset_id":14976679,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681509/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&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="14976679"><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="14976679"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976679; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976679]").text(description); $(".js-view-count[data-work-id=14976679]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976679; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976679']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976679, 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: "abb1b7b69f8112dc0f3a3608323254d4" } } $('.js-work-strip[data-work-id=14976679]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976679,"title":"Heuristic Search for Non-Bottom-Up Tree Structure Prediction","translated_title":"","metadata":{"abstract":"State of the art Tree Structures Prediction techniques rely on bottom-up decoding. These approaches allow the use of context-free features and bottom-up features. We discuss the limitations of mainstream techniques in solving common Natural Language Processing tasks. Then we devise a new framework that goes beyond Bottom-up Decoding, and that allows a better integration of contextual features. Furthermore we design a system that addresses these issues and we test it on Hierarchical Machine Translation, a well known tree structure prediction problem. The structure of the proposed system allows the incorporation of non-bottom-up features and relies on a more sophisticated decoding approach. We show that the proposed approach can find better translations using a smaller portion of the search space."},"translated_abstract":"State of the art Tree Structures Prediction techniques rely on bottom-up decoding. These approaches allow the use of context-free features and bottom-up features. We discuss the limitations of mainstream techniques in solving common Natural Language Processing tasks. Then we devise a new framework that goes beyond Bottom-up Decoding, and that allows a better integration of contextual features. Furthermore we design a system that addresses these issues and we test it on Hierarchical Machine Translation, a well known tree structure prediction problem. The structure of the proposed system allows the incorporation of non-bottom-up features and relies on a more sophisticated decoding approach. We show that the proposed approach can find better translations using a smaller portion of the search space.","internal_url":"https://www.academia.edu/14976679/Heuristic_Search_for_Non_Bottom_Up_Tree_Structure_Prediction","translated_internal_url":"","created_at":"2015-08-17T02:32:11.718-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735408,"work_id":14976679,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083276,"email":"a***o@unige.ch","display_order":0,"name":"Andrea Gesmundo","title":"Heuristic Search for Non-Bottom-Up Tree Structure Prediction"}],"downloadable_attachments":[{"id":43681509,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681509/thumbnails/1.jpg","file_name":"Heuristic_Search_for_Non-Bottom-Up_Tree_20160313-15496-bdxe3r.pdf","download_url":"https://www.academia.edu/attachments/43681509/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Heuristic_Search_for_Non_Bottom_Up_Tree.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681509/Heuristic_Search_for_Non-Bottom-Up_Tree_20160313-15496-bdxe3r-libre.pdf?1457873729=\u0026response-content-disposition=attachment%3B+filename%3DHeuristic_Search_for_Non_Bottom_Up_Tree.pdf\u0026Expires=1732458746\u0026Signature=fpJinabkCUCm8u-wB3QgcuYLLRRCw6091UJK-pNYBzNn1pLWibZ5KogE68-xeXfwnLvigAEThJK83SIduDMqYRbuJZ0LlrO3tThDX7xMeWuVdokXSmbzdVsO9BNPU4EP2wSw1mg5w4s116qpWpfxgPlSbo20pzvG5TKHC0Brm9LS3PQh6BFxHWQbfLctY5S1lodFYQs02CCf9mWQZO6LE0G3IgpdnqP8NwvwRelYwhkOCeUpSQMnLCwwNTJvOpF4ydjaQqqRP9YAq7eAzQvGzX9vKpCEPMO7PIy55sUh5eaNH9TfsKiaElb4lT6qnvrCYxN4n7x3ydO0trCKli0Onw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Heuristic_Search_for_Non_Bottom_Up_Tree_Structure_Prediction","translated_slug":"","page_count":10,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681509,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681509/thumbnails/1.jpg","file_name":"Heuristic_Search_for_Non-Bottom-Up_Tree_20160313-15496-bdxe3r.pdf","download_url":"https://www.academia.edu/attachments/43681509/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Heuristic_Search_for_Non_Bottom_Up_Tree.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681509/Heuristic_Search_for_Non-Bottom-Up_Tree_20160313-15496-bdxe3r-libre.pdf?1457873729=\u0026response-content-disposition=attachment%3B+filename%3DHeuristic_Search_for_Non_Bottom_Up_Tree.pdf\u0026Expires=1732458746\u0026Signature=fpJinabkCUCm8u-wB3QgcuYLLRRCw6091UJK-pNYBzNn1pLWibZ5KogE68-xeXfwnLvigAEThJK83SIduDMqYRbuJZ0LlrO3tThDX7xMeWuVdokXSmbzdVsO9BNPU4EP2wSw1mg5w4s116qpWpfxgPlSbo20pzvG5TKHC0Brm9LS3PQh6BFxHWQbfLctY5S1lodFYQs02CCf9mWQZO6LE0G3IgpdnqP8NwvwRelYwhkOCeUpSQMnLCwwNTJvOpF4ydjaQqqRP9YAq7eAzQvGzX9vKpCEPMO7PIy55sUh5eaNH9TfsKiaElb4lT6qnvrCYxN4n7x3ydO0trCKli0Onw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[],"urls":[{"id":6897529,"url":"https://www.researchgate.net/profile/James_Henderson8/publication/221013234_Heuristic_Search_for_Non-Bottom-Up_Tree_Structure_Prediction/links/00b49518b81d715307000000.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="14976678"><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/14976678/Unsupervised_semantic_role_induction_with_global_role_ordering"><img alt="Research paper thumbnail of Unsupervised semantic role induction with global role ordering" class="work-thumbnail" src="https://attachments.academia-assets.com/43681472/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/14976678/Unsupervised_semantic_role_induction_with_global_role_ordering">Unsupervised semantic role induction with global role ordering</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">We propose a probabilistic generative model for unsupervised semantic role induction, which integ...</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">We propose a probabilistic generative model for unsupervised semantic role induction, which integrates local role assignment decisions and a global role ordering decision in a unified model. The role sequence is divided into intervals based on the notion of primary roles, and each interval generates a sequence of secondary roles and syntactic constituents using local features. The global role ordering consists of the sequence of primary roles only, thus making it a partial ordering.</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="47ff8e78ff1972bfdaf486d78eebe289" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681472,"asset_id":14976678,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681472/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&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="14976678"><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="14976678"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976678; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976678]").text(description); $(".js-view-count[data-work-id=14976678]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976678; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976678']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976678, 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: "47ff8e78ff1972bfdaf486d78eebe289" } } $('.js-work-strip[data-work-id=14976678]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976678,"title":"Unsupervised semantic role induction with global role ordering","translated_title":"","metadata":{"abstract":"We propose a probabilistic generative model for unsupervised semantic role induction, which integrates local role assignment decisions and a global role ordering decision in a unified model. The role sequence is divided into intervals based on the notion of primary roles, and each interval generates a sequence of secondary roles and syntactic constituents using local features. The global role ordering consists of the sequence of primary roles only, thus making it a partial ordering."},"translated_abstract":"We propose a probabilistic generative model for unsupervised semantic role induction, which integrates local role assignment decisions and a global role ordering decision in a unified model. The role sequence is divided into intervals based on the notion of primary roles, and each interval generates a sequence of secondary roles and syntactic constituents using local features. The global role ordering consists of the sequence of primary roles only, thus making it a partial ordering.","internal_url":"https://www.academia.edu/14976678/Unsupervised_semantic_role_induction_with_global_role_ordering","translated_internal_url":"","created_at":"2015-08-17T02:32:11.580-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735523,"work_id":14976678,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083285,"email":"n***g@unige.ch","display_order":0,"name":"N. Garg","title":"Unsupervised semantic role induction with global role ordering"}],"downloadable_attachments":[{"id":43681472,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681472/thumbnails/1.jpg","file_name":"Unsupervised_semantic_role_induction_wit20160313-6133-9j9gn1.pdf","download_url":"https://www.academia.edu/attachments/43681472/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Unsupervised_semantic_role_induction_wit.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681472/Unsupervised_semantic_role_induction_wit20160313-6133-9j9gn1-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DUnsupervised_semantic_role_induction_wit.pdf\u0026Expires=1732458746\u0026Signature=eUDbrm2s1XhQzLqnGY-u2ckHK9B3K-Zb9bAYq7a-PsLmgEC30lce8EYTIYls9Z~w0l~nV-75Ed8z0tVyTqqrLh8y5R0T6uJKhn-jkJinS8tz01m941STEz8Qsu6wuTkLpfjvvAuOtbFgOLoa2LMxVCFb2J5uoTQUNnGqTGbC4gTekVqF2ce3lBkbA4Zj1jOMq1YFjIhYWuDp8Yvndd2YdfLCjBSSGRGzfyLMvpwhhAWQKoAZPfDZwaxnyA0rYDqmdZjSs3hIqc79WU-WzmUK15mpVZENWARlMScN2l72PtdXzWIjKC60TRqBxMVVKS0JjDrQsi69HeAvaHhi8nLhiA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Unsupervised_semantic_role_induction_with_global_role_ordering","translated_slug":"","page_count":5,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681472,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681472/thumbnails/1.jpg","file_name":"Unsupervised_semantic_role_induction_wit20160313-6133-9j9gn1.pdf","download_url":"https://www.academia.edu/attachments/43681472/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Niw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Unsupervised_semantic_role_induction_wit.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681472/Unsupervised_semantic_role_induction_wit20160313-6133-9j9gn1-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DUnsupervised_semantic_role_induction_wit.pdf\u0026Expires=1732458746\u0026Signature=eUDbrm2s1XhQzLqnGY-u2ckHK9B3K-Zb9bAYq7a-PsLmgEC30lce8EYTIYls9Z~w0l~nV-75Ed8z0tVyTqqrLh8y5R0T6uJKhn-jkJinS8tz01m941STEz8Qsu6wuTkLpfjvvAuOtbFgOLoa2LMxVCFb2J5uoTQUNnGqTGbC4gTekVqF2ce3lBkbA4Zj1jOMq1YFjIhYWuDp8Yvndd2YdfLCjBSSGRGzfyLMvpwhhAWQKoAZPfDZwaxnyA0rYDqmdZjSs3hIqc79WU-WzmUK15mpVZENWARlMScN2l72PtdXzWIjKC60TRqBxMVVKS0JjDrQsi69HeAvaHhi8nLhiA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[],"urls":[{"id":6897526,"url":"https://www.researchgate.net/profile/James_Henderson8/publication/262309398_Unsupervised_semantic_role_induction_with_global_role_ordering/links/551aec300cf251c35b50348a.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="14976677"><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/14976677/The_PARLANCE_mobile_application_for_interactive_search_in_English_and_Mandarin"><img alt="Research paper thumbnail of The PARLANCE mobile application for interactive search in English and Mandarin" 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/14976677/The_PARLANCE_mobile_application_for_interactive_search_in_English_and_Mandarin">The PARLANCE mobile application for interactive search in English and Mandarin</a></div><div class="wp-workCard_item wp-workCard--coauthors"><span>by </span><span><a class="" data-click-track="profile-work-strip-authors" href="https://independent.academia.edu/JamesHenderson28">James Henderson</a>, <a class="" data-click-track="profile-work-strip-authors" href="https://hw.academia.edu/VerenaRieser">Verena Rieser</a>, and <a class="" data-click-track="profile-work-strip-authors" href="https://independent.academia.edu/MajidYazdani4">Majid Yazdani</a></span></div><div class="wp-workCard_item"><span>Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)</span><span>, 2014</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="14976677"><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="14976677"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976677; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976677]").text(description); $(".js-view-count[data-work-id=14976677]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976677; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976677']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976677, 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" } } $('.js-work-strip[data-work-id=14976677]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976677,"title":"The PARLANCE mobile application for interactive search in English and Mandarin","translated_title":"","metadata":{"publication_date":{"day":null,"month":null,"year":2014,"errors":{}},"publication_name":"Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)"},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976677/The_PARLANCE_mobile_application_for_interactive_search_in_English_and_Mandarin","translated_internal_url":"","created_at":"2015-08-17T02:32:11.493-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735374,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":1067708,"co_author_invite_id":null,"email":"v***r@hw.ac.uk","affiliation":"Heriot-Watt University","display_order":6291456,"name":"Verena Rieser","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735383,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":12926397,"co_author_invite_id":null,"email":"s***g@gmail.com","affiliation":"University of Liverpool","display_order":7340032,"name":"steve young","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735393,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":11042832,"co_author_invite_id":null,"email":"d***5@hotmail.com","display_order":7864320,"name":"Steve Young","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735452,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083281,"email":"o***n@hwac.uk","display_order":8126464,"name":"Oliver Lemon","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735471,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":695287,"email":"o***n@inf.ed.ac.uk","display_order":8257536,"name":"Oliver Lemon","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735475,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":510167,"email":"p***a@cs.vu.nl","display_order":8323072,"name":"Peter Mika","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735477,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":19073,"co_author_invite_id":null,"email":"p***s@gmail.com","affiliation":"National Technical University of Athens","display_order":8355840,"name":"Panos Alexopoulos","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735479,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":5458864,"co_author_invite_id":null,"email":"m***0@gmail.com","display_order":8372224,"name":"majid yazdani","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735480,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083282,"email":"h***e@research.att.com","display_order":8380416,"name":"Helen Hastie","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735481,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083283,"email":"h***e@research.att.com","display_order":8384512,"name":"Helen Hastie","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735482,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":154781,"co_author_invite_id":null,"email":"h***e@hw.ac.uk","affiliation":"Heriot-Watt University","display_order":8386560,"name":"Helen Hastie","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735525,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083286,"email":"c***4@cam.ac.uk","display_order":8387584,"name":"Catherine Breslin","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735526,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":695227,"email":"h***l@ed.ac.uk","display_order":8388096,"name":"Heriberto Cuay谩huitl","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735527,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083287,"email":"n***s@googlemail.com","display_order":8388352,"name":"Nina Dethlefs","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735528,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":34652530,"co_author_invite_id":186493,"email":"m***6@cam.ac.uk","display_order":8388480,"name":"M. Ga拧i膰","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735529,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":189144,"email":"b***2@cam.ac.uk","display_order":8388544,"name":"Blaise Thomson","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735530,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083288,"email":"p***4@cam.ac.uk","display_order":8388576,"name":"Pirros Tsiakoulis","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735531,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083289,"email":"b***n@isoco.com","display_order":8388592,"name":"Boris Villazon-terrazas","title":"The PARLANCE mobile application for interactive search in English and Mandarin"},{"id":4735532,"work_id":14976677,"tagging_user_id":33971246,"tagged_user_id":34068110,"co_author_invite_id":1083290,"email":"m***i@unige.ch","display_order":8388600,"name":"Majid Yazdani","title":"The PARLANCE mobile application for interactive search in English and Mandarin"}],"downloadable_attachments":[],"slug":"The_PARLANCE_mobile_application_for_interactive_search_in_English_and_Mandarin","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[],"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="14976676"><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/14976676/Mixture_model_POMDPs_for_efficient_handling_of_uncertainty_in_dialogue_management"><img alt="Research paper thumbnail of Mixture model POMDPs for efficient handling of uncertainty in dialogue management" class="work-thumbnail" src="https://attachments.academia-assets.com/43681659/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/14976676/Mixture_model_POMDPs_for_efficient_handling_of_uncertainty_in_dialogue_management">Mixture model POMDPs for efficient handling of uncertainty in dialogue management</a></div><div class="wp-workCard_item"><span>Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies Short Papers - HLT '08</span><span>, 2008</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="7110ada4bfb6eb814b68adba26229a76" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681659,"asset_id":14976676,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681659/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976676"><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="14976676"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976676; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976676]").text(description); $(".js-view-count[data-work-id=14976676]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976676; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976676']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976676, 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: "7110ada4bfb6eb814b68adba26229a76" } } $('.js-work-strip[data-work-id=14976676]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976676,"title":"Mixture model POMDPs for efficient handling of uncertainty in dialogue management","translated_title":"","metadata":{"grobid_abstract":"In spoken dialogue systems, Partially Observable Markov Decision Processes (POMDPs) provide a formal framework for making dialogue management decisions under uncertainty, but efficiency and interpretability considerations mean that most current statistical dialogue managers are only MDPs. These MDP systems encode uncertainty explicitly in a single state representation. We formalise such MDP states in terms of distributions over POMDP states, and propose a new dialogue system architecture (Mixture Model POMDPs) which uses mixtures of these distributions to efficiently represent uncertainty. We also provide initial evaluation results (with real users) for this architecture.","publication_date":{"day":null,"month":null,"year":2008,"errors":{}},"publication_name":"Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies Short Papers - HLT '08","grobid_abstract_attachment_id":43681659},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976676/Mixture_model_POMDPs_for_efficient_handling_of_uncertainty_in_dialogue_management","translated_internal_url":"","created_at":"2015-08-17T02:32:11.402-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735447,"work_id":14976676,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083281,"email":"o***n@hwac.uk","display_order":6291456,"name":"Oliver Lemon","title":"Mixture model POMDPs for efficient handling of uncertainty in dialogue management"},{"id":4735467,"work_id":14976676,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":695287,"email":"o***n@inf.ed.ac.uk","display_order":7340032,"name":"Oliver Lemon","title":"Mixture model POMDPs for efficient handling of uncertainty in dialogue management"}],"downloadable_attachments":[{"id":43681659,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681659/thumbnails/1.jpg","file_name":"Mixture_Model_POMDPs_for_Efficient_Handl20160313-4265-jvrivt.pdf","download_url":"https://www.academia.edu/attachments/43681659/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Mixture_model_POMDPs_for_efficient_handl.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681659/Mixture_Model_POMDPs_for_Efficient_Handl20160313-4265-jvrivt-libre.pdf?1457873716=\u0026response-content-disposition=attachment%3B+filename%3DMixture_model_POMDPs_for_efficient_handl.pdf\u0026Expires=1732458746\u0026Signature=WJyGybBF1X23-H05Bp1jI3LBBPta7i~Sw13EFgtZsMPgCE~m-jB97Ub-2wbAt59EZsk3BaB8Cab6Q5eDRwSBOCbgFL3LfHQJwqIp-Q3r-tjiMq4EdF9DVdvqUIq~F-vV5aHdbdLd8ScPX8qh7jMmloWbIGjeDVQaKo6cOKeZ34BkyQekMzoqaMGMkMok0A7SdmJQbh0I~FGPuC6LmjDcTF6UhoYN2-b5EjifxzP-0-2JqOw-5ulouyZ8TXgT9U7BCQ5sENLsZeQbv0j0mdszs~~fpY0CyJPfUewyusedBNBIsPaxLC7y6G43js8DRcZEDWGcFeLpf3C0XybEOroZlA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Mixture_model_POMDPs_for_efficient_handling_of_uncertainty_in_dialogue_management","translated_slug":"","page_count":4,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681659,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681659/thumbnails/1.jpg","file_name":"Mixture_Model_POMDPs_for_Efficient_Handl20160313-4265-jvrivt.pdf","download_url":"https://www.academia.edu/attachments/43681659/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Mixture_model_POMDPs_for_efficient_handl.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681659/Mixture_Model_POMDPs_for_Efficient_Handl20160313-4265-jvrivt-libre.pdf?1457873716=\u0026response-content-disposition=attachment%3B+filename%3DMixture_model_POMDPs_for_efficient_handl.pdf\u0026Expires=1732458747\u0026Signature=Xw6pLfBustuYZ8WFxekf5iHiImDjZdhwud3NwSZm6dmxeEHNNzES7rVuen6qVXmr1A~vRiOXIqwZs1qm4GNqmFSEsX~8se95eeeaYuCdDlXiH8jQIB~UVd0LZLGZOjaNq~L325QmiD1yS3Yh3CyFNP0x1XicC3RCzeF1mMlR2oOD9ZYqPVLy87OVQ6C8xL3fQ43Nl65FLgUhDnrxctybOJ8i-NaAze-12XnI9uJbscpim0Y6uzIreyoCloh8r-SPPWOkCVOTDQMfttgthbhDo-xjh6fKyVRHRVaAvK3qjGPcc5cLIHWU0tBXY2jwuOiyJOvpCDUqRRkyVeK6nPW8Aw__\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":1688,"name":"Reinforcement Learning","url":"https://www.academia.edu/Documents/in/Reinforcement_Learning"},{"id":2008,"name":"Machine Learning","url":"https://www.academia.edu/Documents/in/Machine_Learning"},{"id":3268,"name":"Computational Linguistics","url":"https://www.academia.edu/Documents/in/Computational_Linguistics"},{"id":5337,"name":"Agent Based Simulation","url":"https://www.academia.edu/Documents/in/Agent_Based_Simulation"},{"id":15084,"name":"Statistical machine learning","url":"https://www.academia.edu/Documents/in/Statistical_machine_learning"},{"id":37228,"name":"Multimodal Interfaces","url":"https://www.academia.edu/Documents/in/Multimodal_Interfaces"},{"id":38181,"name":"AI","url":"https://www.academia.edu/Documents/in/AI"}],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="14976675"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/14976675/Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning"><img alt="Research paper thumbnail of Undirected Machine Translation with Discriminative Reinforcement Learning" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/14976675/Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning">Undirected Machine Translation with Discriminative Reinforcement Learning</a></div><div class="wp-workCard_item"><span>Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics</span><span>, 2014</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="14976675"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="14976675"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976675; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976675]").text(description); $(".js-view-count[data-work-id=14976675]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976675; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976675']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976675, 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" } } $('.js-work-strip[data-work-id=14976675]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976675,"title":"Undirected Machine Translation with Discriminative Reinforcement Learning","translated_title":"","metadata":{"publication_date":{"day":null,"month":null,"year":2014,"errors":{}},"publication_name":"Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics"},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976675/Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning","translated_internal_url":"","created_at":"2015-08-17T02:32:11.300-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735405,"work_id":14976675,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083276,"email":"a***o@unige.ch","display_order":0,"name":"Andrea Gesmundo","title":"Undirected Machine Translation with Discriminative Reinforcement Learning"}],"downloadable_attachments":[],"slug":"Undirected_Machine_Translation_with_Discriminative_Reinforcement_Learning","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[],"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="14976674"><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/14976674/Data_Driven_Methods_for_Spoken_Language_Understanding"><img alt="Research paper thumbnail of Data-Driven Methods for Spoken Language Understanding" 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/14976674/Data_Driven_Methods_for_Spoken_Language_Understanding">Data-Driven Methods for Spoken Language Understanding</a></div><div class="wp-workCard_item"><span>Data-Driven Methods for Adaptive Spoken Dialogue Systems</span><span>, 2012</span></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">Spoken dialogue systems need to be able to interpret the spoken input from the user. This is done...</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">Spoken dialogue systems need to be able to interpret the spoken input from the user. This is done by mapping the user&amp;amp;#x27;s spoken utterance to a representation of the meaning of that utterance, and then passing this representation to the dialogue manager. This process begins with the application of automatic speech recognition (ASR) technology, which maps the speech to hypotheses about the sequence of words in the utterance. It is then the job of spoken language understanding (SLU) to map the word recognition hypotheses to ...</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="14976674"><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="14976674"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976674; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976674]").text(description); $(".js-view-count[data-work-id=14976674]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976674; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976674']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976674, 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" } } $('.js-work-strip[data-work-id=14976674]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976674,"title":"Data-Driven Methods for Spoken Language Understanding","translated_title":"","metadata":{"abstract":"Spoken dialogue systems need to be able to interpret the spoken input from the user. This is done by mapping the user\u0026amp;amp;#x27;s spoken utterance to a representation of the meaning of that utterance, and then passing this representation to the dialogue manager. This process begins with the application of automatic speech recognition (ASR) technology, which maps the speech to hypotheses about the sequence of words in the utterance. It is then the job of spoken language understanding (SLU) to map the word recognition hypotheses to ...","publication_date":{"day":null,"month":null,"year":2012,"errors":{}},"publication_name":"Data-Driven Methods for Adaptive Spoken Dialogue Systems"},"translated_abstract":"Spoken dialogue systems need to be able to interpret the spoken input from the user. This is done by mapping the user\u0026amp;amp;#x27;s spoken utterance to a representation of the meaning of that utterance, and then passing this representation to the dialogue manager. This process begins with the application of automatic speech recognition (ASR) technology, which maps the speech to hypotheses about the sequence of words in the utterance. It is then the job of spoken language understanding (SLU) to map the word recognition hypotheses to ...","internal_url":"https://www.academia.edu/14976674/Data_Driven_Methods_for_Spoken_Language_Understanding","translated_internal_url":"","created_at":"2015-08-17T02:32:11.203-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735426,"work_id":14976674,"tagging_user_id":33971246,"tagged_user_id":1230797,"co_author_invite_id":null,"email":"f***k@gmail.com","affiliation":"Charles University, Prague","display_order":0,"name":"Filip Jurcicek","title":"Data-Driven Methods for Spoken Language Understanding"}],"downloadable_attachments":[],"slug":"Data_Driven_Methods_for_Spoken_Language_Understanding","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[],"urls":[]}, dispatcherData: dispatcherData }); $(this).data('initialized', true); } }); $a.trackClickSource(".js-work-strip-work-link", "profile_work_strip") }); </script> <div class="js-work-strip profile--work_container" data-work-id="14976673"><div class="profile--work_thumbnail hidden-xs"><a class="js-work-strip-work-link" data-click-track="profile-work-strip-thumbnail" rel="nofollow" href="https://www.academia.edu/14976673/Graph_Based_Seed_Set_Expansion_for_Relation_Extraction_Using_Random_Walk_Hitting_Times"><img alt="Research paper thumbnail of Graph-Based Seed Set Expansion for Relation Extraction Using Random Walk Hitting Times" class="work-thumbnail" src="https://a.academia-assets.com/images/blank-paper.jpg" /></a></div><div class="wp-workCard wp-workCard_itemContainer"><div class="wp-workCard_item wp-workCard--title"><a class="js-work-strip-work-link text-gray-darker" data-click-track="profile-work-strip-title" rel="nofollow" href="https://www.academia.edu/14976673/Graph_Based_Seed_Set_Expansion_for_Relation_Extraction_Using_Random_Walk_Hitting_Times">Graph-Based Seed Set Expansion for Relation Extraction Using Random Walk Hitting Times</a></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><span class="wp-workCard--action visible-if-viewed-by-owner inline-block" style="display: none;"><span class="js-profile-work-strip-edit-button-wrapper profile-work-strip-edit-button-wrapper" data-work-id="14976673"><a class="js-profile-work-strip-edit-button" tabindex="0"><span><i class="fa fa-pencil"></i></span><span>Edit</span></a></span></span><span id="work-strip-rankings-button-container"></span></div><div class="wp-workCard_item wp-workCard--stats"><span><span><span class="js-view-count view-count u-mr2x" data-work-id="14976673"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976673; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976673]").text(description); $(".js-view-count[data-work-id=14976673]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976673; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976673']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976673, 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" } } $('.js-work-strip[data-work-id=14976673]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976673,"title":"Graph-Based Seed Set Expansion for Relation Extraction Using Random Walk Hitting Times","translated_title":"","metadata":{},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976673/Graph_Based_Seed_Set_Expansion_for_Relation_Extraction_Using_Random_Walk_Hitting_Times","translated_internal_url":"","created_at":"2015-08-17T02:32:11.118-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735535,"work_id":14976673,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1011476,"email":"s***0@sms.ed.ac.uk","display_order":0,"name":"Joel Lang","title":"Graph-Based Seed Set Expansion for Relation Extraction Using Random Walk Hitting Times"}],"downloadable_attachments":[],"slug":"Graph_Based_Seed_Set_Expansion_for_Relation_Extraction_Using_Random_Walk_Hitting_Times","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[],"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="14976672"><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/14976672/Efficient_Computation_of_Mean_Truncated_Hitting_Times_on_Very_Large_Graphs"><img alt="Research paper thumbnail of Efficient Computation of Mean Truncated Hitting Times on Very Large Graphs" 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/14976672/Efficient_Computation_of_Mean_Truncated_Hitting_Times_on_Very_Large_Graphs">Efficient Computation of Mean Truncated Hitting Times on Very Large Graphs</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">ABSTRACT Previous work has shown the effectiveness of random walk hitting times as a measure of d...</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 Previous work has shown the effectiveness of random walk hitting times as a measure of dissimilarity in a variety of graph-based learning problems such as collaborative filtering, query suggestion or finding paraphrases. However, application of hitting times has been limited to small datasets because of computational restrictions. This paper develops a new approximation algorithm with which hitting times can be computed on very large, disk-resident graphs, making their application possible to problems which were previously out of reach. This will potentially benefit a range of large-scale problems.</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="14976672"><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="14976672"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976672; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976672]").text(description); $(".js-view-count[data-work-id=14976672]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976672; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976672']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976672, 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" } } $('.js-work-strip[data-work-id=14976672]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976672,"title":"Efficient Computation of Mean Truncated Hitting Times on Very Large Graphs","translated_title":"","metadata":{"abstract":"ABSTRACT Previous work has shown the effectiveness of random walk hitting times as a measure of dissimilarity in a variety of graph-based learning problems such as collaborative filtering, query suggestion or finding paraphrases. However, application of hitting times has been limited to small datasets because of computational restrictions. This paper develops a new approximation algorithm with which hitting times can be computed on very large, disk-resident graphs, making their application possible to problems which were previously out of reach. This will potentially benefit a range of large-scale problems."},"translated_abstract":"ABSTRACT Previous work has shown the effectiveness of random walk hitting times as a measure of dissimilarity in a variety of graph-based learning problems such as collaborative filtering, query suggestion or finding paraphrases. However, application of hitting times has been limited to small datasets because of computational restrictions. This paper develops a new approximation algorithm with which hitting times can be computed on very large, disk-resident graphs, making their application possible to problems which were previously out of reach. This will potentially benefit a range of large-scale problems.","internal_url":"https://www.academia.edu/14976672/Efficient_Computation_of_Mean_Truncated_Hitting_Times_on_Very_Large_Graphs","translated_internal_url":"","created_at":"2015-08-17T02:32:11.030-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735534,"work_id":14976672,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1011476,"email":"s***0@sms.ed.ac.uk","display_order":0,"name":"Joel Lang","title":"Efficient Computation of Mean Truncated Hitting Times on Very Large Graphs"}],"downloadable_attachments":[],"slug":"Efficient_Computation_of_Mean_Truncated_Hitting_Times_on_Very_Large_Graphs","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[],"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="14976671"><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/14976671/Automatic_annotation_of_COMMUNICATOR_dialogue_data_for_learning_dialogue_strategies_and_user_simulations"><img alt="Research paper thumbnail of Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations" class="work-thumbnail" src="https://attachments.academia-assets.com/43681660/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/14976671/Automatic_annotation_of_COMMUNICATOR_dialogue_data_for_learning_dialogue_strategies_and_user_simulations">Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations</a></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="6fa09afa279d79c4c97bb86de0b5e528" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681660,"asset_id":14976671,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681660/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976671"><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="14976671"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976671; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976671]").text(description); $(".js-view-count[data-work-id=14976671]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976671; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976671']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976671, 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: "6fa09afa279d79c4c97bb86de0b5e528" } } $('.js-work-strip[data-work-id=14976671]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976671,"title":"Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations","translated_title":"","metadata":{"grobid_abstract":"We present and evaluate an automatic annotation system which builds \"Information State Update\" (ISU) representations of dialogue context for the COMMUNICATOR (2000 and 2001) corpora of humanmachine dialogues (approx 2300 dialogues). The purposes of this annotation are to generate training data for reinforcement learning (RL) of dialogue policies, to generate data for building user simulations, and to evaluate different dialogue strategies against a baseline. The automatic annotation system uses the DIPPER dialogue manager. This produces annotations of user inputs and dialogue context representations. We present a detailed example, and then evaluate our annotations, with respect to the task completion metrics of the original corpus. The resulting data has been used to train user simulations and to learn successful dialogue strategies.","publication_date":{"day":null,"month":null,"year":2005,"errors":{}},"grobid_abstract_attachment_id":43681660},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976671/Automatic_annotation_of_COMMUNICATOR_dialogue_data_for_learning_dialogue_strategies_and_user_simulations","translated_internal_url":"","created_at":"2015-08-17T02:32:10.937-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735455,"work_id":14976671,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083281,"email":"o***n@hwac.uk","display_order":6291456,"name":"Oliver Lemon","title":"Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations"},{"id":4735474,"work_id":14976671,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":695287,"email":"o***n@inf.ed.ac.uk","display_order":7340032,"name":"Oliver Lemon","title":"Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations"},{"id":4735515,"work_id":14976671,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":114196,"email":"k***a@ict.usc.edu","display_order":7864320,"name":"Kallirroi Georgila","title":"Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations"}],"downloadable_attachments":[{"id":43681660,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681660/thumbnails/1.jpg","file_name":"08-Lemon.pdf","download_url":"https://www.academia.edu/attachments/43681660/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Automatic_annotation_of_COMMUNICATOR_dia.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681660/08-Lemon-libre.pdf?1457873716=\u0026response-content-disposition=attachment%3B+filename%3DAutomatic_annotation_of_COMMUNICATOR_dia.pdf\u0026Expires=1732458747\u0026Signature=AA5LZmUTT4a8hr~LBKgGf79jlAtF7TMLrVatcraM-DAU~X6Vtc-knKDaScsyX8apaMXO8ee4QbCnPAMJ2XLseBLMAUMjd-TSz0zJjeqdXhnqBfQ-QPAV8~ayf08AqhWM4VKh7mj4V3QEdMJ4HnTgS6F4hBH1EkFzjKU974rYveXpPIKsuCAvChs30WTQg7Iw0jtvWB5myXOEmlIMmNPP~UigExA4mm82-XMeZMR188rxDThuVoxVem0EkQ~0haYO1dvlzhOJZH0kkj9Bt8iwKnGYbyZiDw7foD-pHuv6O7E60c9F7ti8GZPmNDbjOaP8U5607Am3ID1iDvslN46xPw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Automatic_annotation_of_COMMUNICATOR_dialogue_data_for_learning_dialogue_strategies_and_user_simulations","translated_slug":"","page_count":8,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681660,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681660/thumbnails/1.jpg","file_name":"08-Lemon.pdf","download_url":"https://www.academia.edu/attachments/43681660/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Automatic_annotation_of_COMMUNICATOR_dia.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681660/08-Lemon-libre.pdf?1457873716=\u0026response-content-disposition=attachment%3B+filename%3DAutomatic_annotation_of_COMMUNICATOR_dia.pdf\u0026Expires=1732458747\u0026Signature=AA5LZmUTT4a8hr~LBKgGf79jlAtF7TMLrVatcraM-DAU~X6Vtc-knKDaScsyX8apaMXO8ee4QbCnPAMJ2XLseBLMAUMjd-TSz0zJjeqdXhnqBfQ-QPAV8~ayf08AqhWM4VKh7mj4V3QEdMJ4HnTgS6F4hBH1EkFzjKU974rYveXpPIKsuCAvChs30WTQg7Iw0jtvWB5myXOEmlIMmNPP~UigExA4mm82-XMeZMR188rxDThuVoxVem0EkQ~0haYO1dvlzhOJZH0kkj9Bt8iwKnGYbyZiDw7foD-pHuv6O7E60c9F7ti8GZPmNDbjOaP8U5607Am3ID1iDvslN46xPw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"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":1688,"name":"Reinforcement Learning","url":"https://www.academia.edu/Documents/in/Reinforcement_Learning"},{"id":2008,"name":"Machine Learning","url":"https://www.academia.edu/Documents/in/Machine_Learning"},{"id":5337,"name":"Agent Based Simulation","url":"https://www.academia.edu/Documents/in/Agent_Based_Simulation"},{"id":37228,"name":"Multimodal Interfaces","url":"https://www.academia.edu/Documents/in/Multimodal_Interfaces"},{"id":38181,"name":"AI","url":"https://www.academia.edu/Documents/in/AI"},{"id":1900565,"name":"Automatic Annotation","url":"https://www.academia.edu/Documents/in/Automatic_Annotation"}],"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="14976670"><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/14976670/Final_Report_on_Multimodal_Experiments_Part_II_Experiments_for_data_collection_and_technology_evaluation"><img alt="Research paper thumbnail of Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation" class="work-thumbnail" src="https://attachments.academia-assets.com/43681463/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/14976670/Final_Report_on_Multimodal_Experiments_Part_II_Experiments_for_data_collection_and_technology_evaluation">Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation</a></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="38f052ab146cdb23984c936a4d724541" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681463,"asset_id":14976670,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681463/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976670"><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="14976670"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976670; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976670]").text(description); $(".js-view-count[data-work-id=14976670]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976670; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976670']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976670, 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: "38f052ab146cdb23984c936a4d724541" } } $('.js-work-strip[data-work-id=14976670]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976670,"title":"Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation","translated_title":"","metadata":{"publication_date":{"day":null,"month":null,"year":2006,"errors":{}}},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976670/Final_Report_on_Multimodal_Experiments_Part_II_Experiments_for_data_collection_and_technology_evaluation","translated_internal_url":"","created_at":"2015-08-17T02:32:10.817-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735376,"work_id":14976670,"tagging_user_id":33971246,"tagged_user_id":1067708,"co_author_invite_id":null,"email":"v***r@hw.ac.uk","affiliation":"Heriot-Watt University","display_order":6291456,"name":"Verena Rieser","title":"Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation"},{"id":4735454,"work_id":14976670,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":1083281,"email":"o***n@hwac.uk","display_order":7340032,"name":"Oliver Lemon","title":"Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation"},{"id":4735473,"work_id":14976670,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":695287,"email":"o***n@inf.ed.ac.uk","display_order":7864320,"name":"Oliver Lemon","title":"Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation"},{"id":4735514,"work_id":14976670,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":114196,"email":"k***a@ict.usc.edu","display_order":8126464,"name":"Kallirroi Georgila","title":"Final Report on Multimodal Experiments-Part II: Experiments for data collection and technology evaluation"}],"downloadable_attachments":[{"id":43681463,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681463/thumbnails/1.jpg","file_name":"D6_4-part2.pdf","download_url":"https://www.academia.edu/attachments/43681463/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Final_Report_on_Multimodal_Experiments_P.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681463/D6_4-part2-libre.pdf?1457873737=\u0026response-content-disposition=attachment%3B+filename%3DFinal_Report_on_Multimodal_Experiments_P.pdf\u0026Expires=1732458747\u0026Signature=bJCdTAoEXFHOK7KzsiXT4bLGnUHPlvl86eRpCnjSmCUnvqcm07KXtrFfKaiES-siurPh9gqQXupFcrgNiNd4YMxDtx-iJ4VvvEWXQFluwj0nYEF2UmmXpeHjfQ7AvC7rhdHAvZLH-eNfiiAwK6sy7-xXoZpGz22hB5uScKM5XOSPpGs3rLE4WsJt3RRTy0AASZ-CCDVHplytFfSubC-PvtNu~JgK2hv1ubOyRxC2MdAISnDAhZM5Bas0g1e7q35Qu3iijTq0~flgtSQ2FmYo29~R9smFqBuD1VwH0BxijBJPFMeBBlHUp3uk998D5WWUOJjj4RgWF4Y~iU~MfkSxyA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Final_Report_on_Multimodal_Experiments_Part_II_Experiments_for_data_collection_and_technology_evaluation","translated_slug":"","page_count":66,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681463,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681463/thumbnails/1.jpg","file_name":"D6_4-part2.pdf","download_url":"https://www.academia.edu/attachments/43681463/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Final_Report_on_Multimodal_Experiments_P.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681463/D6_4-part2-libre.pdf?1457873737=\u0026response-content-disposition=attachment%3B+filename%3DFinal_Report_on_Multimodal_Experiments_P.pdf\u0026Expires=1732458747\u0026Signature=bJCdTAoEXFHOK7KzsiXT4bLGnUHPlvl86eRpCnjSmCUnvqcm07KXtrFfKaiES-siurPh9gqQXupFcrgNiNd4YMxDtx-iJ4VvvEWXQFluwj0nYEF2UmmXpeHjfQ7AvC7rhdHAvZLH-eNfiiAwK6sy7-xXoZpGz22hB5uScKM5XOSPpGs3rLE4WsJt3RRTy0AASZ-CCDVHplytFfSubC-PvtNu~JgK2hv1ubOyRxC2MdAISnDAhZM5Bas0g1e7q35Qu3iijTq0~flgtSQ2FmYo29~R9smFqBuD1VwH0BxijBJPFMeBBlHUp3uk998D5WWUOJjj4RgWF4Y~iU~MfkSxyA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":153168,"name":"Data Collection","url":"https://www.academia.edu/Documents/in/Data_Collection"}],"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="14976669"><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/14976669/Incremental_Bayesian_networks_for_structure_prediction"><img alt="Research paper thumbnail of Incremental Bayesian networks for structure prediction" class="work-thumbnail" src="https://attachments.academia-assets.com/43681484/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/14976669/Incremental_Bayesian_networks_for_structure_prediction">Incremental Bayesian networks for structure prediction</a></div><div class="wp-workCard_item"><span>Proceedings of the 24th international conference on Machine learning - ICML '07</span><span>, 2007</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="b22b0db8f7ee2604cd1f3704467d550b" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681484,"asset_id":14976669,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681484/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976669"><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="14976669"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976669; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976669]").text(description); $(".js-view-count[data-work-id=14976669]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976669; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976669']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976669, 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: "b22b0db8f7ee2604cd1f3704467d550b" } } $('.js-work-strip[data-work-id=14976669]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976669,"title":"Incremental Bayesian networks for structure prediction","translated_title":"","metadata":{"grobid_abstract":"We propose a class of graphical models appropriate for structure prediction problems where the model structure is a function of the output structure. Incremental Sigmoid Belief Networks (ISBNs) avoid the need to sum over the possible model structures by using directed arcs and incrementally specifying the model structure. Exact inference in such directed models is not tractable, but we derive two efficient approximations based on mean field methods, which prove effective in artificial experiments. We then demonstrate their effectiveness on a benchmark natural language parsing task, where they achieve state-of-the-art accuracy. Also, the model which is a closer approximation to an ISBN has better parsing accuracy, suggesting that ISBNs are an appropriate abstract model of structure prediction tasks.","publication_date":{"day":null,"month":null,"year":2007,"errors":{}},"publication_name":"Proceedings of the 24th international conference on Machine learning - ICML '07","grobid_abstract_attachment_id":43681484},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976669/Incremental_Bayesian_networks_for_structure_prediction","translated_internal_url":"","created_at":"2015-08-17T02:32:10.712-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735502,"work_id":14976669,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":57191,"email":"t***v@mmci.uni-saarland.de","display_order":0,"name":"Ivan Titov","title":"Incremental Bayesian networks for structure prediction"}],"downloadable_attachments":[{"id":43681484,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681484/thumbnails/1.jpg","file_name":"351.pdf","download_url":"https://www.academia.edu/attachments/43681484/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Incremental_Bayesian_networks_for_struct.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681484/351-libre.pdf?1457873730=\u0026response-content-disposition=attachment%3B+filename%3DIncremental_Bayesian_networks_for_struct.pdf\u0026Expires=1732458747\u0026Signature=b5dOQL~xSLYAjWcpx6-ZKB~euFhB9fK5PB18vVk6ktF0hL7n39bDqdb58o2MLf1d4RJitt~OSNL5NjAoHC4Jmddoof6auy~~VHhPN7NdFI1BcHqElVOBMprfH5cJ1SEFCbDfWUchbF0J2fOZ3Cm6DRl-DDs3kBPMEfxUww4Ldfu8FRRGJJKc2Hslx9iJbD0Hr9tkMYZC4Uljh2rS2eUCE0wfnpV9LYy1cdSht682esBwPGGiQ6k-RJr8hBc1oz7q5byX1Vj8Dk0MlMhVH5IaRs551wz620XfcSZb~4~7Hn7eJbvtcD7w3ze1M7IKZ2eIqRS600ZvVm4LuVtueFP1sw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Incremental_Bayesian_networks_for_structure_prediction","translated_slug":"","page_count":8,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681484,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681484/thumbnails/1.jpg","file_name":"351.pdf","download_url":"https://www.academia.edu/attachments/43681484/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Incremental_Bayesian_networks_for_struct.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681484/351-libre.pdf?1457873730=\u0026response-content-disposition=attachment%3B+filename%3DIncremental_Bayesian_networks_for_struct.pdf\u0026Expires=1732458747\u0026Signature=b5dOQL~xSLYAjWcpx6-ZKB~euFhB9fK5PB18vVk6ktF0hL7n39bDqdb58o2MLf1d4RJitt~OSNL5NjAoHC4Jmddoof6auy~~VHhPN7NdFI1BcHqElVOBMprfH5cJ1SEFCbDfWUchbF0J2fOZ3Cm6DRl-DDs3kBPMEfxUww4Ldfu8FRRGJJKc2Hslx9iJbD0Hr9tkMYZC4Uljh2rS2eUCE0wfnpV9LYy1cdSht682esBwPGGiQ6k-RJr8hBc1oz7q5byX1Vj8Dk0MlMhVH5IaRs551wz620XfcSZb~4~7Hn7eJbvtcD7w3ze1M7IKZ2eIqRS600ZvVm4LuVtueFP1sw__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":4600,"name":"Protein Structure Prediction","url":"https://www.academia.edu/Documents/in/Protein_Structure_Prediction"},{"id":274599,"name":"Bayesian Network","url":"https://www.academia.edu/Documents/in/Bayesian_Network"},{"id":315917,"name":"Natural Language Parsing","url":"https://www.academia.edu/Documents/in/Natural_Language_Parsing"},{"id":663297,"name":"Bayesian Belief Network","url":"https://www.academia.edu/Documents/in/Bayesian_Belief_Network"},{"id":886652,"name":"Graphical Model","url":"https://www.academia.edu/Documents/in/Graphical_Model"}],"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="14976668"><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/14976668/Porting_statistical_parsers_with_data_defined_kernels"><img alt="Research paper thumbnail of Porting statistical parsers with data-defined kernels" class="work-thumbnail" src="https://attachments.academia-assets.com/43681661/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/14976668/Porting_statistical_parsers_with_data_defined_kernels">Porting statistical parsers with data-defined kernels</a></div><div class="wp-workCard_item"><span>Proceedings of the Tenth Conference on Computational Natural Language Learning - CoNLL-X '06</span><span>, 2006</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="8d8119239a2def6c35916d7efd143f46" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681661,"asset_id":14976668,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681661/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976668"><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="14976668"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976668; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976668]").text(description); $(".js-view-count[data-work-id=14976668]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976668; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976668']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976668, 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: "8d8119239a2def6c35916d7efd143f46" } } $('.js-work-strip[data-work-id=14976668]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976668,"title":"Porting statistical parsers with data-defined kernels","translated_title":"","metadata":{"grobid_abstract":"Previous results have shown disappointing performance when porting a parser trained on one domain to another domain where only a small amount of data is available. We propose the use of data-defined kernels as a way to exploit statistics from a source domain while still specializing a parser to a target domain. A probabilistic model trained on the source domain (and possibly also the target domain) is used to define a kernel, which is then used in a large margin classifier trained only on the target domain. With a SVM classifier and a neural network probabilistic model, this method achieves improved performance over the probabilistic model alone.","publication_date":{"day":null,"month":null,"year":2006,"errors":{}},"publication_name":"Proceedings of the Tenth Conference on Computational Natural Language Learning - CoNLL-X '06","grobid_abstract_attachment_id":43681661},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976668/Porting_statistical_parsers_with_data_defined_kernels","translated_internal_url":"","created_at":"2015-08-17T02:32:10.591-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735539,"work_id":14976668,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":57191,"email":"t***v@mmci.uni-saarland.de","display_order":0,"name":"Ivan Titov","title":"Porting statistical parsers with data-defined kernels"}],"downloadable_attachments":[{"id":43681661,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681661/thumbnails/1.jpg","file_name":"titov_conll06.pdf","download_url":"https://www.academia.edu/attachments/43681661/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Porting_statistical_parsers_with_data_de.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681661/titov_conll06-libre.pdf?1457873716=\u0026response-content-disposition=attachment%3B+filename%3DPorting_statistical_parsers_with_data_de.pdf\u0026Expires=1732458747\u0026Signature=doTZ8KPP67zUGT2ww2BCigtjBu~k8XxFZUQc0~2saI10pe4EOZ2ZKtoh3WyRy1hQDjRaKvNl3MlC4UMwK6BeO909vj3-TfaZ9MYHsvdC~QFI2eCG1W8ASEtb8J~BSP~cjk3iCI6odNOp~9Xhxeg6OzE6DNowLPq1PUd5XFcZVyUpFKVa7w~41MSRJJeHpO2a5lRb8NN0PdlfCBEWf5sa2AEDzSeBLVMn3BK3L8zOG9hSi0aucGDo190r5Q9zdlbRjTI8Lg90DYrU-JYH6XWSMZ3NaJxpo2ztC~fsRj7gppjbCzh1gn5Z2vzXI0eA5bWGyPX3A5JTsJtuPO-VIuGl~g__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Porting_statistical_parsers_with_data_defined_kernels","translated_slug":"","page_count":8,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681661,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681661/thumbnails/1.jpg","file_name":"titov_conll06.pdf","download_url":"https://www.academia.edu/attachments/43681661/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Porting_statistical_parsers_with_data_de.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681661/titov_conll06-libre.pdf?1457873716=\u0026response-content-disposition=attachment%3B+filename%3DPorting_statistical_parsers_with_data_de.pdf\u0026Expires=1732458747\u0026Signature=doTZ8KPP67zUGT2ww2BCigtjBu~k8XxFZUQc0~2saI10pe4EOZ2ZKtoh3WyRy1hQDjRaKvNl3MlC4UMwK6BeO909vj3-TfaZ9MYHsvdC~QFI2eCG1W8ASEtb8J~BSP~cjk3iCI6odNOp~9Xhxeg6OzE6DNowLPq1PUd5XFcZVyUpFKVa7w~41MSRJJeHpO2a5lRb8NN0PdlfCBEWf5sa2AEDzSeBLVMn3BK3L8zOG9hSi0aucGDo190r5Q9zdlbRjTI8Lg90DYrU-JYH6XWSMZ3NaJxpo2ztC~fsRj7gppjbCzh1gn5Z2vzXI0eA5bWGyPX3A5JTsJtuPO-VIuGl~g__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":26066,"name":"Neural Network","url":"https://www.academia.edu/Documents/in/Neural_Network"},{"id":99531,"name":"Probabilistic Model Checking","url":"https://www.academia.edu/Documents/in/Probabilistic_Model_Checking"}],"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="14976667"><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/14976667/A_Latent_Variable_Model_for_Generative_Dependency_Parsing"><img alt="Research paper thumbnail of A Latent Variable Model for Generative Dependency Parsing" class="work-thumbnail" src="https://attachments.academia-assets.com/43681477/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/14976667/A_Latent_Variable_Model_for_Generative_Dependency_Parsing">A Latent Variable Model for Generative Dependency Parsing</a></div><div class="wp-workCard_item"><span>Text, Speech and Language Technology</span><span>, 2010</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="ab27089df63b41f5649dc629934fd02f" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681477,"asset_id":14976667,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681477/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976667"><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="14976667"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976667; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976667]").text(description); $(".js-view-count[data-work-id=14976667]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976667; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976667']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976667, 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: "ab27089df63b41f5649dc629934fd02f" } } $('.js-work-strip[data-work-id=14976667]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976667,"title":"A Latent Variable Model for Generative Dependency Parsing","translated_title":"","metadata":{"grobid_abstract":"We propose a generative dependency parsing model which uses binary latent variables to induce conditioning features. To define this model we use a recently proposed class of Bayesian Networks for structured prediction, Incremental Sigmoid Belief Networks. We demonstrate that the proposed model achieves state-of-the-art results on three different languages. We also demonstrate that the features induced by the ISBN's latent variables are crucial to this success, and show that the proposed model is particularly good on long dependencies.","publication_date":{"day":null,"month":null,"year":2010,"errors":{}},"publication_name":"Text, Speech and Language Technology","grobid_abstract_attachment_id":43681477},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976667/A_Latent_Variable_Model_for_Generative_Dependency_Parsing","translated_internal_url":"","created_at":"2015-08-17T02:32:10.469-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735493,"work_id":14976667,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":57191,"email":"t***v@mmci.uni-saarland.de","display_order":0,"name":"Ivan Titov","title":"A Latent Variable Model for Generative Dependency Parsing"}],"downloadable_attachments":[{"id":43681477,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681477/thumbnails/1.jpg","file_name":"A_Latent_Variable_Model_for_Generative_D20160313-6151-131tkf4.pdf","download_url":"https://www.academia.edu/attachments/43681477/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"A_Latent_Variable_Model_for_Generative_D.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681477/A_Latent_Variable_Model_for_Generative_D20160313-6151-131tkf4-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DA_Latent_Variable_Model_for_Generative_D.pdf\u0026Expires=1732458747\u0026Signature=HPGJdCTMoyuFAO-CId3PQmtAmdQAD5DyKlXVSm8EshS7hFuBYxWN1V1wBHPjFyybaWFjA5re~GFb3i-mV~jx0XSmoFphiezhfHJ3d-hNkU0kvFH0Jt4O73lSrzfRChmivVV5GLOWH7xtdeXutmvsB9krVI9p6ZW6G-nhDZRic0bBYK0wqHJwYS61MonBtlwff60ZhP2VoX8siAiqglvAAu4RxP8qfXatpmQb-8Xh0d8Wr7E~hIfiBWCdHj2fs7Yl6odfoyklNhJDgPlIYNORKQlVl4RHtTFw-bgjCK-4Ow2U04XiRw3cla89Rl9H9f6gZcCLq-SM5LtnS31cW1GnYA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"A_Latent_Variable_Model_for_Generative_Dependency_Parsing","translated_slug":"","page_count":12,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681477,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681477/thumbnails/1.jpg","file_name":"A_Latent_Variable_Model_for_Generative_D20160313-6151-131tkf4.pdf","download_url":"https://www.academia.edu/attachments/43681477/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"A_Latent_Variable_Model_for_Generative_D.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681477/A_Latent_Variable_Model_for_Generative_D20160313-6151-131tkf4-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DA_Latent_Variable_Model_for_Generative_D.pdf\u0026Expires=1732458747\u0026Signature=HPGJdCTMoyuFAO-CId3PQmtAmdQAD5DyKlXVSm8EshS7hFuBYxWN1V1wBHPjFyybaWFjA5re~GFb3i-mV~jx0XSmoFphiezhfHJ3d-hNkU0kvFH0Jt4O73lSrzfRChmivVV5GLOWH7xtdeXutmvsB9krVI9p6ZW6G-nhDZRic0bBYK0wqHJwYS61MonBtlwff60ZhP2VoX8siAiqglvAAu4RxP8qfXatpmQb-8Xh0d8Wr7E~hIfiBWCdHj2fs7Yl6odfoyklNhJDgPlIYNORKQlVl4RHtTFw-bgjCK-4Ow2U04XiRw3cla89Rl9H9f6gZcCLq-SM5LtnS31cW1GnYA__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":1432,"name":"Natural Language Processing","url":"https://www.academia.edu/Documents/in/Natural_Language_Processing"},{"id":286240,"name":"Minimum Spanning Tree","url":"https://www.academia.edu/Documents/in/Minimum_Spanning_Tree"},{"id":297057,"name":"Dependency Parsing","url":"https://www.academia.edu/Documents/in/Dependency_Parsing"}],"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="14976666"><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/14976666/for_Large_Categorization_Problems"><img alt="Research paper thumbnail of for Large Categorization Problems" 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/14976666/for_Large_Categorization_Problems">for Large Categorization Problems</a></div><div class="wp-workCard_item"><span class="js-work-more-abstract-truncated">In multi-class categorization problems with a very large or unbounded number of classes, it is of...</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">In multi-class categorization problems with a very large or unbounded number of classes, it is often not compu- tationally feasible to train and/or test a kernel-based classifier. One solution is to use a fast computation to pre-select a subset of the classes for reranking with a kernel method, but even then tractability can be a problem. We investigate using trained</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="14976666"><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="14976666"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976666; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976666]").text(description); $(".js-view-count[data-work-id=14976666]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976666; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976666']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976666, 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" } } $('.js-work-strip[data-work-id=14976666]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976666,"title":"for Large Categorization Problems","translated_title":"","metadata":{"abstract":"In multi-class categorization problems with a very large or unbounded number of classes, it is often not compu- tationally feasible to train and/or test a kernel-based classifier. One solution is to use a fast computation to pre-select a subset of the classes for reranking with a kernel method, but even then tractability can be a problem. We investigate using trained","publication_date":{"day":null,"month":null,"year":2000,"errors":{}}},"translated_abstract":"In multi-class categorization problems with a very large or unbounded number of classes, it is often not compu- tationally feasible to train and/or test a kernel-based classifier. One solution is to use a fast computation to pre-select a subset of the classes for reranking with a kernel method, but even then tractability can be a problem. We investigate using trained","internal_url":"https://www.academia.edu/14976666/for_Large_Categorization_Problems","translated_internal_url":"","created_at":"2015-08-17T02:32:10.285-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735503,"work_id":14976666,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":57191,"email":"t***v@mmci.uni-saarland.de","display_order":0,"name":"Ivan Titov","title":"for Large Categorization Problems"}],"downloadable_attachments":[],"slug":"for_Large_Categorization_Problems","translated_slug":"","page_count":null,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[],"research_interests":[{"id":26066,"name":"Neural Network","url":"https://www.academia.edu/Documents/in/Neural_Network"},{"id":194045,"name":"Multi-layer Perceptron","url":"https://www.academia.edu/Documents/in/Multi-layer_Perceptron"},{"id":315917,"name":"Natural Language Parsing","url":"https://www.academia.edu/Documents/in/Natural_Language_Parsing"},{"id":1837730,"name":"Neural Network Model","url":"https://www.academia.edu/Documents/in/Neural_Network_Model"}],"urls":[{"id":5217564,"url":"http://homepages.inf.ed.ac.uk/jhender6/papers/titov_ijcnn05.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="14976664"><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/14976664/Data_defined_kernels_for_parse_reranking_derived_from_probabilistic_models"><img alt="Research paper thumbnail of Data-defined kernels for parse reranking derived from probabilistic models" class="work-thumbnail" src="https://attachments.academia-assets.com/43681471/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/14976664/Data_defined_kernels_for_parse_reranking_derived_from_probabilistic_models">Data-defined kernels for parse reranking derived from probabilistic models</a></div><div class="wp-workCard_item"><span>Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05</span><span>, 2005</span></div><div class="wp-workCard_item wp-workCard--actions"><span class="work-strip-bookmark-button-container"></span><a id="9c3b6394f8c711154596a9c1ed31f4ac" class="wp-workCard--action" rel="nofollow" data-click-track="profile-work-strip-download" data-download="{"attachment_id":43681471,"asset_id":14976664,"asset_type":"Work","button_location":"profile"}" href="https://www.academia.edu/attachments/43681471/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&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="14976664"><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="14976664"><i class="fa fa-spinner fa-spin"></i></span><script>$(function () { var workId = 14976664; window.Academia.workViewCountsFetcher.queue(workId, function (count) { var description = window.$h.commaizeInt(count) + " " + window.$h.pluralize(count, 'View'); $(".js-view-count[data-work-id=14976664]").text(description); $(".js-view-count[data-work-id=14976664]").attr('title', description).tooltip(); }); });</script></span></span><span><span class="percentile-widget hidden"><span class="u-mr2x work-percentile"></span></span><script>$(function () { var workId = 14976664; window.Academia.workPercentilesFetcher.queue(workId, function (percentileText) { var container = $(".js-work-strip[data-work-id='14976664']"); container.find('.work-percentile').text(percentileText.charAt(0).toUpperCase() + percentileText.slice(1)); container.find('.percentile-widget').show(); container.find('.percentile-widget').removeClass('hidden'); }); });</script></span><span><script>$(function() { new Works.PaperRankView({ workId: 14976664, 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: "9c3b6394f8c711154596a9c1ed31f4ac" } } $('.js-work-strip[data-work-id=14976664]').each(function() { if (!$(this).data('initialized')) { new WowProfile.WorkStripView({ el: this, workJSON: {"id":14976664,"title":"Data-defined kernels for parse reranking derived from probabilistic models","translated_title":"","metadata":{"grobid_abstract":"Previous research applying kernel methods to natural language parsing have focussed on proposing kernels over parse trees, which are hand-crafted based on domain knowledge and computational considerations. In this paper we propose a method for defining kernels in terms of a probabilistic model of parsing. This model is then trained, so that the parameters of the probabilistic model reflect the generalizations in the training data. The method we propose then uses these trained parameters to define a kernel for reranking parse trees. In experiments, we use a neural network based statistical parser as the probabilistic model, and use the resulting kernel with the Voted Perceptron algorithm to rerank the top 20 parses from the probabilistic model. This method achieves a significant improvement over the accuracy of the probabilistic model.","publication_date":{"day":null,"month":null,"year":2005,"errors":{}},"publication_name":"Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05","grobid_abstract_attachment_id":43681471},"translated_abstract":null,"internal_url":"https://www.academia.edu/14976664/Data_defined_kernels_for_parse_reranking_derived_from_probabilistic_models","translated_internal_url":"","created_at":"2015-08-17T02:32:09.222-07:00","preview_url":null,"current_user_can_edit":null,"current_user_is_owner":null,"owner_id":33971246,"coauthors_can_edit":true,"document_type":"paper","co_author_tags":[{"id":4735492,"work_id":14976664,"tagging_user_id":33971246,"tagged_user_id":null,"co_author_invite_id":57191,"email":"t***v@mmci.uni-saarland.de","display_order":0,"name":"Ivan Titov","title":"Data-defined kernels for parse reranking derived from probabilistic models"}],"downloadable_attachments":[{"id":43681471,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681471/thumbnails/1.jpg","file_name":"P05-1023.pdf","download_url":"https://www.academia.edu/attachments/43681471/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Data_defined_kernels_for_parse_reranking.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681471/P05-1023-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DData_defined_kernels_for_parse_reranking.pdf\u0026Expires=1732458747\u0026Signature=ayVvecc9OLYV6avi3aIv1Ztye-eLzp4CmbX5aHKNdESA296WhBvTolro3zN0OcV1Ve-dmnSih5jKcDIjF6KfR-1E438wMAtJatXpI2uYXbqp717-HKkL02Key7Je2U2IaiBHs67fePacrD7Jtw2NJfyneNoQ-zNHVhWb85f2pnZbRzkLYAIjj78YrhJZAt0WFaaFr2TS57cPir2Ai8KQUu1nESyGvTMffnxXiNZXC3leIT-EPpg5G9MnZvl9OeY9Pn8ygYijPErFgvTclSsUslE190ayhmdot~~hajcQw7viqj-mLLPME94oBTTkgbUVwWbgC0sOAmbgqtsXPY4OcQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"slug":"Data_defined_kernels_for_parse_reranking_derived_from_probabilistic_models","translated_slug":"","page_count":8,"language":"en","content_type":"Work","owner":{"id":33971246,"first_name":"James","middle_initials":null,"last_name":"Henderson","page_name":"JamesHenderson28","domain_name":"independent","created_at":"2015-08-17T02:17:56.804-07:00","display_name":"James Henderson","url":"https://independent.academia.edu/JamesHenderson28"},"attachments":[{"id":43681471,"title":"","file_type":"pdf","scribd_thumbnail_url":"https://attachments.academia-assets.com/43681471/thumbnails/1.jpg","file_name":"P05-1023.pdf","download_url":"https://www.academia.edu/attachments/43681471/download_file?st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&st=MTczMjQ1NTE0Nyw4LjIyMi4yMDguMTQ2&","bulk_download_file_name":"Data_defined_kernels_for_parse_reranking.pdf","bulk_download_url":"https://d1wqtxts1xzle7.cloudfront.net/43681471/P05-1023-libre.pdf?1457873731=\u0026response-content-disposition=attachment%3B+filename%3DData_defined_kernels_for_parse_reranking.pdf\u0026Expires=1732458747\u0026Signature=ayVvecc9OLYV6avi3aIv1Ztye-eLzp4CmbX5aHKNdESA296WhBvTolro3zN0OcV1Ve-dmnSih5jKcDIjF6KfR-1E438wMAtJatXpI2uYXbqp717-HKkL02Key7Je2U2IaiBHs67fePacrD7Jtw2NJfyneNoQ-zNHVhWb85f2pnZbRzkLYAIjj78YrhJZAt0WFaaFr2TS57cPir2Ai8KQUu1nESyGvTMffnxXiNZXC3leIT-EPpg5G9MnZvl9OeY9Pn8ygYijPErFgvTclSsUslE190ayhmdot~~hajcQw7viqj-mLLPME94oBTTkgbUVwWbgC0sOAmbgqtsXPY4OcQ__\u0026Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA"}],"research_interests":[{"id":26066,"name":"Neural Network","url":"https://www.academia.edu/Documents/in/Neural_Network"},{"id":99531,"name":"Probabilistic Model Checking","url":"https://www.academia.edu/Documents/in/Probabilistic_Model_Checking"},{"id":315917,"name":"Natural Language Parsing","url":"https://www.academia.edu/Documents/in/Natural_Language_Parsing"}],"urls":[]}, 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: "62cd8ef279801a18c186bddcbe13a8793f16278e1406a0dcbf81b0aaeb7503ae", });</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="yhz+D8mi4JcbNxZMv82p7K//Tqys3GA4rLL0Q/szX8xDOwxEquhgyw//fDd8e/osgO6oeHSAA+jbvZUUimKm2g==" 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://independent.academia.edu/JamesHenderson28" 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="qAEVmoTPqOdYhTkkT43DnsrS39ABcRj/S6dboK+kIJMhJufR54Uou0xNU1+MO5Be5cM5BNktey88qDr33vXZhQ==" 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>