Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 53 results for author: <span class="mathjax">Nguyen, L T</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Nguyen%2C+L+T">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Nguyen, L T"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Nguyen%2C+L+T&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Nguyen, L T"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Nguyen%2C+L+T&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Nguyen%2C+L+T&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Nguyen%2C+L+T&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.03458">arXiv:2410.03458</a> <span> [<a href="https://arxiv.org/pdf/2410.03458">pdf</a>, <a href="https://arxiv.org/format/2410.03458">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Multi-Dialect Vietnamese: Task, Dataset, Baseline Models and Challenges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Van+Dinh%2C+N">Nguyen Van Dinh</a>, <a href="/search/cs?searchtype=author&query=Dang%2C+T+C">Thanh Chi Dang</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luan Thanh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+K">Kiet Van Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.03458v1-abstract-short" style="display: inline;"> Vietnamese, a low-resource language, is typically categorized into three primary dialect groups that belong to Northern, Central, and Southern Vietnam. However, each province within these regions exhibits its own distinct pronunciation variations. Despite the existence of various speech recognition datasets, none of them has provided a fine-grained classification of the 63 dialects specific to ind… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03458v1-abstract-full').style.display = 'inline'; document.getElementById('2410.03458v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03458v1-abstract-full" style="display: none;"> Vietnamese, a low-resource language, is typically categorized into three primary dialect groups that belong to Northern, Central, and Southern Vietnam. However, each province within these regions exhibits its own distinct pronunciation variations. Despite the existence of various speech recognition datasets, none of them has provided a fine-grained classification of the 63 dialects specific to individual provinces of Vietnam. To address this gap, we introduce Vietnamese Multi-Dialect (ViMD) dataset, a novel comprehensive dataset capturing the rich diversity of 63 provincial dialects spoken across Vietnam. Our dataset comprises 102.56 hours of audio, consisting of approximately 19,000 utterances, and the associated transcripts contain over 1.2 million words. To provide benchmarks and simultaneously demonstrate the challenges of our dataset, we fine-tune state-of-the-art pre-trained models for two downstream tasks: (1) Dialect identification and (2) Speech recognition. The empirical results suggest two implications including the influence of geographical factors on dialects, and the constraints of current approaches in speech recognition tasks involving multi-dialect speech data. Our dataset is available for research purposes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03458v1-abstract-full').style.display = 'none'; document.getElementById('2410.03458v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Main EMNLP 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.03169">arXiv:2409.03169</a> <span> [<a href="https://arxiv.org/pdf/2409.03169">pdf</a>, <a href="https://arxiv.org/format/2409.03169">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Formal Languages and Automata Theory">cs.FL</span> </div> </div> <p class="title is-5 mathjax"> Two or three things I know about tree transducers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.03169v2-abstract-short" style="display: inline;"> You might know that the name "tree transducers" refers to various kinds of automata that compute functions on ranked trees, i.e. terms over a first-order signature. But have you ever wondered about how to remember what a macro tree transducer does? Or what are the connections between top-down tree(-to-string) transducers, multi bottom-up tree(-to-string) transducers, tree-walking transducers, (i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03169v2-abstract-full').style.display = 'inline'; document.getElementById('2409.03169v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.03169v2-abstract-full" style="display: none;"> You might know that the name "tree transducers" refers to various kinds of automata that compute functions on ranked trees, i.e. terms over a first-order signature. But have you ever wondered about how to remember what a macro tree transducer does? Or what are the connections between top-down tree(-to-string) transducers, multi bottom-up tree(-to-string) transducers, tree-walking transducers, (invisible) pebble tree transducers, monadic second-order transductions, unfoldings of rooted directed acyclic graphs (i.e. term graphs) -- and what happens when the functions that they compute are composed? The answers may be found in old papers (mostly coauthored by Engelfriet), but maybe you can save some time by first looking at this short note. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03169v2-abstract-full').style.display = 'none'; document.getElementById('2409.03169v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Unpublished note, compiling known results</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.02555">arXiv:2406.02555</a> <span> [<a href="https://arxiv.org/pdf/2406.02555">pdf</a>, <a href="https://arxiv.org/ps/2406.02555">ps</a>, <a href="https://arxiv.org/format/2406.02555">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> PhoWhisper: Automatic Speech Recognition for Vietnamese </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Le%2C+T">Thanh-Thien Le</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Linh The Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D+Q">Dat Quoc Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.02555v1-abstract-short" style="display: inline;"> We introduce PhoWhisper in five versions for Vietnamese automatic speech recognition. PhoWhisper's robustness is achieved through fine-tuning the Whisper model on an 844-hour dataset that encompasses diverse Vietnamese accents. Our experimental study demonstrates state-of-the-art performances of PhoWhisper on benchmark Vietnamese ASR datasets. We have open-sourced PhoWhisper at: https://github.com… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.02555v1-abstract-full').style.display = 'inline'; document.getElementById('2406.02555v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.02555v1-abstract-full" style="display: none;"> We introduce PhoWhisper in five versions for Vietnamese automatic speech recognition. PhoWhisper's robustness is achieved through fine-tuning the Whisper model on an 844-hour dataset that encompasses diverse Vietnamese accents. Our experimental study demonstrates state-of-the-art performances of PhoWhisper on benchmark Vietnamese ASR datasets. We have open-sourced PhoWhisper at: https://github.com/VinAIResearch/PhoWhisper <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.02555v1-abstract-full').style.display = 'none'; document.getElementById('2406.02555v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to ICLR 2024 Tiny Papers Track</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.14141">arXiv:2405.14141</a> <span> [<a href="https://arxiv.org/pdf/2405.14141">pdf</a>, <a href="https://arxiv.org/format/2405.14141">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> ViHateT5: Enhancing Hate Speech Detection in Vietnamese With A Unified Text-to-Text Transformer Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luan Thanh Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.14141v2-abstract-short" style="display: inline;"> Recent advancements in hate speech detection (HSD) in Vietnamese have made significant progress, primarily attributed to the emergence of transformer-based pre-trained language models, particularly those built on the BERT architecture. However, the necessity for specialized fine-tuned models has resulted in the complexity and fragmentation of developing a multitasking HSD system. Moreover, most cu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.14141v2-abstract-full').style.display = 'inline'; document.getElementById('2405.14141v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.14141v2-abstract-full" style="display: none;"> Recent advancements in hate speech detection (HSD) in Vietnamese have made significant progress, primarily attributed to the emergence of transformer-based pre-trained language models, particularly those built on the BERT architecture. However, the necessity for specialized fine-tuned models has resulted in the complexity and fragmentation of developing a multitasking HSD system. Moreover, most current methodologies focus on fine-tuning general pre-trained models, primarily trained on formal textual datasets like Wikipedia, which may not accurately capture human behavior on online platforms. In this research, we introduce ViHateT5, a T5-based model pre-trained on our proposed large-scale domain-specific dataset named VOZ-HSD. By harnessing the power of a text-to-text architecture, ViHateT5 can tackle multiple tasks using a unified model and achieve state-of-the-art performance across all standard HSD benchmarks in Vietnamese. Our experiments also underscore the significance of label distribution in pre-training data on model efficacy. We provide our experimental materials for research purposes, including the VOZ-HSD dataset, pre-trained checkpoint, the unified HSD-multitask ViHateT5 model, and related source code on GitHub publicly. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.14141v2-abstract-full').style.display = 'none'; document.getElementById('2405.14141v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at ACL'2024 (Findings)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.05276">arXiv:2404.05276</a> <span> [<a href="https://arxiv.org/pdf/2404.05276">pdf</a>, <a href="https://arxiv.org/ps/2404.05276">ps</a>, <a href="https://arxiv.org/format/2404.05276">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> </div> </div> <p class="title is-5 mathjax"> On the complexity of normalization for the planar $位$-calculus </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Das%2C+A">Anupam Das</a>, <a href="/search/cs?searchtype=author&query=Mazza%2C+D">Damiano Mazza</a>, <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a>, <a href="/search/cs?searchtype=author&query=Zeilberger%2C+N">Noam Zeilberger</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.05276v1-abstract-short" style="display: inline;"> We sketch a tentative proof of P-completeness for the $尾$-convertibility problem on untyped planar (a.k.a. ordered or non-commutative) $位$-terms. </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.05276v1-abstract-full" style="display: none;"> We sketch a tentative proof of P-completeness for the $尾$-convertibility problem on untyped planar (a.k.a. ordered or non-commutative) $位$-terms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.05276v1-abstract-full').style.display = 'none'; document.getElementById('2404.05276v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Abstract for the Trends in Linear Logic and Applications 2023 workshop, meant to be expanded into a proper paper in the future</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.05265">arXiv:2404.05265</a> <span> [<a href="https://arxiv.org/pdf/2404.05265">pdf</a>, <a href="https://arxiv.org/format/2404.05265">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Formal Languages and Automata Theory">cs.FL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Logic">math.LO</span> </div> </div> <p class="title is-5 mathjax"> Function spaces for orbit-finite sets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Boja%C5%84czyk%2C+M">Miko艂aj Boja艅czyk</a>, <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a>, <a href="/search/cs?searchtype=author&query=Stefa%C5%84ski%2C+R">Rafa艂 Stefa艅ski</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.05265v1-abstract-short" style="display: inline;"> Orbit-finite sets are a generalisation of finite sets, and as such support many operations allowed for finite sets, such as pairing, quotienting, or taking subsets. However, they do not support function spaces, i.e. if X and Y are orbit-finite sets, then the space of finitely supported functions from X to Y is not orbit-finite. In this paper we propose two solutions to this problem: one is obtaine… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.05265v1-abstract-full').style.display = 'inline'; document.getElementById('2404.05265v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.05265v1-abstract-full" style="display: none;"> Orbit-finite sets are a generalisation of finite sets, and as such support many operations allowed for finite sets, such as pairing, quotienting, or taking subsets. However, they do not support function spaces, i.e. if X and Y are orbit-finite sets, then the space of finitely supported functions from X to Y is not orbit-finite. In this paper we propose two solutions to this problem: one is obtained by generalising the notion of orbit-finite set, and the other one is obtained by restricting it. In both cases, function spaces and the original closure properties are retained. Curiously, both solutions are "linear": the generalisation is based on linear algebra, while the restriction is based on linear logic. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.05265v1-abstract-full').style.display = 'none'; document.getElementById('2404.05265v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.14918">arXiv:2403.14918</a> <span> [<a href="https://arxiv.org/pdf/2403.14918">pdf</a>, <a href="https://arxiv.org/format/2403.14918">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Deep learning-based method for weather forecasting: A case study in Itoshima </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cheng%2C+Y">Yuzhong Cheng</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T+H">Linh Thi Hoai Nguyen</a>, <a href="/search/cs?searchtype=author&query=Ozaki%2C+A">Akinori Ozaki</a>, <a href="/search/cs?searchtype=author&query=Ta%2C+T+V">Ton Viet Ta</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.14918v1-abstract-short" style="display: inline;"> Accurate weather forecasting is of paramount importance for a wide range of practical applications, drawing substantial scientific and societal interest. However, the intricacies of weather systems pose substantial challenges to accurate predictions. This research introduces a multilayer perceptron model tailored for weather forecasting in Itoshima, Kyushu, Japan. Our meticulously designed archite… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.14918v1-abstract-full').style.display = 'inline'; document.getElementById('2403.14918v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.14918v1-abstract-full" style="display: none;"> Accurate weather forecasting is of paramount importance for a wide range of practical applications, drawing substantial scientific and societal interest. However, the intricacies of weather systems pose substantial challenges to accurate predictions. This research introduces a multilayer perceptron model tailored for weather forecasting in Itoshima, Kyushu, Japan. Our meticulously designed architecture demonstrates superior performance compared to existing models, surpassing benchmarks such as Long Short-Term Memory and Recurrent Neural Networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.14918v1-abstract-full').style.display = 'none'; document.getElementById('2403.14918v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.05854">arXiv:2402.05854</a> <span> [<a href="https://arxiv.org/pdf/2402.05854">pdf</a>, <a href="https://arxiv.org/format/2402.05854">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Formal Languages and Automata Theory">cs.FL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> </div> </div> <p class="title is-5 mathjax"> (Almost) Affine Higher-Order Tree Transducers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D+T">L锚 Th脿nh D农ng Tito Nguy锚n</a>, <a href="/search/cs?searchtype=author&query=Vanoni%2C+G">Gabriele Vanoni</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.05854v1-abstract-short" style="display: inline;"> We investigate the tree-to-tree functions computed by \enquote{affine$位$-transducers}: tree automata whose memory consists of an affine $位$-term instead of a finite state. They can be seen as variations on Gallot, Lemay and Salvati's Linear High-Order Deterministic Tree Transducers. When the memory is almost purely affine (\textit{脿 la} Kanazawa), we show that these machines can be translated to t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.05854v1-abstract-full').style.display = 'inline'; document.getElementById('2402.05854v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.05854v1-abstract-full" style="display: none;"> We investigate the tree-to-tree functions computed by \enquote{affine$位$-transducers}: tree automata whose memory consists of an affine $位$-term instead of a finite state. They can be seen as variations on Gallot, Lemay and Salvati's Linear High-Order Deterministic Tree Transducers. When the memory is almost purely affine (\textit{脿 la} Kanazawa), we show that these machines can be translated to tree-walking transducers (and with a purely affine memory, we get a reversible tree-walking transducer). This leads to a proof of an inexpressivity conjecture of \titocecilia on \enquote{implicit automata} in an affine $位$-calculus. The key technical tool in our proofs is the Interaction Abstract Machine (IAM), an operational avatar of the \enquote{geometry of interaction} semantics of linear logic. We work with ad-hoc specializations to (almost) affine $位$-terms of a tree-generating version of the IAM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.05854v1-abstract-full').style.display = 'none'; document.getElementById('2402.05854v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.01198">arXiv:2402.01198</a> <span> [<a href="https://arxiv.org/pdf/2402.01198">pdf</a>, <a href="https://arxiv.org/format/2402.01198">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Physical Layer Location Privacy in SIMO Communication Using Fake Paths Injection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+T+D">Trong Duy Tran</a>, <a href="/search/cs?searchtype=author&query=Da+Costa%2C+M+F">Maxime Ferreira Da Costa</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Linh Trung Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.01198v1-abstract-short" style="display: inline;"> Fake path injection is an emerging paradigm for inducing privacy over wireless networks. In this paper, fake paths are injected by the transmitter into a SIMO multipath communication channel to preserve her physical location from an eavesdropper. A novel statistical privacy metric is defined as the ratio between the largest (resp. smallest) eigenvalues of Bob's (resp. Eve's) Cram茅r-Rao lower bound… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01198v1-abstract-full').style.display = 'inline'; document.getElementById('2402.01198v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.01198v1-abstract-full" style="display: none;"> Fake path injection is an emerging paradigm for inducing privacy over wireless networks. In this paper, fake paths are injected by the transmitter into a SIMO multipath communication channel to preserve her physical location from an eavesdropper. A novel statistical privacy metric is defined as the ratio between the largest (resp. smallest) eigenvalues of Bob's (resp. Eve's) Cram茅r-Rao lower bound on the SIMO multipath channel parameters to assess the privacy enhancements. Leveraging the spectral properties of generalized Vandermonde matrices, bounds on the privacy margin of the proposed scheme are derived. Specifically, it is shown that the privacy margin increases quadratically in the inverse of the separation between the true and the fake paths under Eve's perspective. Numerical simulations further showcase the approach's benefit. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01198v1-abstract-full').style.display = 'none'; document.getElementById('2402.01198v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.11001">arXiv:2311.11001</a> <span> [<a href="https://arxiv.org/pdf/2311.11001">pdf</a>, <a href="https://arxiv.org/format/2311.11001">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Gendec: A Machine Learning-based Framework for Gender Detection from Japanese Names </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pham%2C+D+T">Duong Tien Pham</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luan Thanh Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.11001v1-abstract-short" style="display: inline;"> Every human has their own name, a fundamental aspect of their identity and cultural heritage. The name often conveys a wealth of information, including details about an individual's background, ethnicity, and, especially, their gender. By detecting gender through the analysis of names, researchers can unlock valuable insights into linguistic patterns and cultural norms, which can be applied to pra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.11001v1-abstract-full').style.display = 'inline'; document.getElementById('2311.11001v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.11001v1-abstract-full" style="display: none;"> Every human has their own name, a fundamental aspect of their identity and cultural heritage. The name often conveys a wealth of information, including details about an individual's background, ethnicity, and, especially, their gender. By detecting gender through the analysis of names, researchers can unlock valuable insights into linguistic patterns and cultural norms, which can be applied to practical applications. Hence, this work presents a novel dataset for Japanese name gender detection comprising 64,139 full names in romaji, hiragana, and kanji forms, along with their biological genders. Moreover, we propose Gendec, a framework for gender detection from Japanese names that leverages diverse approaches, including traditional machine learning techniques or cutting-edge transfer learning models, to predict the gender associated with Japanese names accurately. Through a thorough investigation, the proposed framework is expected to be effective and serve potential applications in various domains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.11001v1-abstract-full').style.display = 'none'; document.getElementById('2311.11001v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper is accepted for presentation at ISDA'23</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.02945">arXiv:2311.02945</a> <span> [<a href="https://arxiv.org/pdf/2311.02945">pdf</a>, <a href="https://arxiv.org/ps/2311.02945">ps</a>, <a href="https://arxiv.org/format/2311.02945">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> PhoGPT: Generative Pre-training for Vietnamese </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+D+Q">Dat Quoc Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Linh The Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+C">Chi Tran</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D+N">Dung Ngoc Nguyen</a>, <a href="/search/cs?searchtype=author&query=Phung%2C+D">Dinh Phung</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+H">Hung Bui</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.02945v3-abstract-short" style="display: inline;"> We open-source a state-of-the-art 4B-parameter generative model series for Vietnamese, which includes the base pre-trained monolingual model PhoGPT-4B and its chat variant, PhoGPT-4B-Chat. The base model, PhoGPT-4B, with exactly 3.7B parameters, is pre-trained from scratch on a Vietnamese corpus of 102B tokens, with an 8192 context length, employing a vocabulary of 20480 token types. The chat vari… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.02945v3-abstract-full').style.display = 'inline'; document.getElementById('2311.02945v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.02945v3-abstract-full" style="display: none;"> We open-source a state-of-the-art 4B-parameter generative model series for Vietnamese, which includes the base pre-trained monolingual model PhoGPT-4B and its chat variant, PhoGPT-4B-Chat. The base model, PhoGPT-4B, with exactly 3.7B parameters, is pre-trained from scratch on a Vietnamese corpus of 102B tokens, with an 8192 context length, employing a vocabulary of 20480 token types. The chat variant, PhoGPT-4B-Chat, is the modeling output obtained by fine-tuning PhoGPT-4B on a dataset of 70K instructional prompts and their responses, along with an additional 290K conversations. In addition, we also demonstrate its superior performance compared to previous open-source models. Our PhoGPT models are available at: https://github.com/VinAIResearch/PhoGPT <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.02945v3-abstract-full').style.display = 'none'; document.getElementById('2311.02945v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">PhoGPT-4B Technical Report - 5 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.18046">arXiv:2310.18046</a> <span> [<a href="https://arxiv.org/pdf/2310.18046">pdf</a>, <a href="https://arxiv.org/format/2310.18046">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> ViCLEVR: A Visual Reasoning Dataset and Hybrid Multimodal Fusion Model for Visual Question Answering in Vietnamese </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+K+V">Khiem Vinh Tran</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+H+P">Hao Phu Phan</a>, <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+K">Kiet Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+N+L+T">Ngan Luu Thuy Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.18046v1-abstract-short" style="display: inline;"> In recent years, Visual Question Answering (VQA) has gained significant attention for its diverse applications, including intelligent car assistance, aiding visually impaired individuals, and document image information retrieval using natural language queries. VQA requires effective integration of information from questions and images to generate accurate answers. Neural models for VQA have made r… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.18046v1-abstract-full').style.display = 'inline'; document.getElementById('2310.18046v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.18046v1-abstract-full" style="display: none;"> In recent years, Visual Question Answering (VQA) has gained significant attention for its diverse applications, including intelligent car assistance, aiding visually impaired individuals, and document image information retrieval using natural language queries. VQA requires effective integration of information from questions and images to generate accurate answers. Neural models for VQA have made remarkable progress on large-scale datasets, with a primary focus on resource-rich languages like English. To address this, we introduce the ViCLEVR dataset, a pioneering collection for evaluating various visual reasoning capabilities in Vietnamese while mitigating biases. The dataset comprises over 26,000 images and 30,000 question-answer pairs (QAs), each question annotated to specify the type of reasoning involved. Leveraging this dataset, we conduct a comprehensive analysis of contemporary visual reasoning systems, offering valuable insights into their strengths and limitations. Furthermore, we present PhoVIT, a comprehensive multimodal fusion that identifies objects in images based on questions. The architecture effectively employs transformers to enable simultaneous reasoning over textual and visual data, merging both modalities at an early model stage. The experimental findings demonstrate that our proposed model achieves state-of-the-art performance across four evaluation metrics. The accompanying code and dataset have been made publicly accessible at \url{https://github.com/kvt0012/ViCLEVR}. This provision seeks to stimulate advancements within the research community, fostering the development of more multimodal fusion algorithms, specifically tailored to address the nuances of low-resource languages, exemplified by Vietnamese. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.18046v1-abstract-full').style.display = 'none'; document.getElementById('2310.18046v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">A pre-print version and submitted to journal</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.00198">arXiv:2308.00198</a> <span> [<a href="https://arxiv.org/pdf/2308.00198">pdf</a>, <a href="https://arxiv.org/format/2308.00198">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Formal Languages and Automata Theory">cs.FL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Programming Languages">cs.PL</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.4230/LIPIcs.CSL.2024.40">10.4230/LIPIcs.CSL.2024.40 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Syntactically and semantically regular languages of lambda-terms coincide through logical relations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Moreau%2C+V">Vincent Moreau</a>, <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.00198v4-abstract-short" style="display: inline;"> A fundamental theme in automata theory is regular languages of words and trees, and their many equivalent definitions. Salvati has proposed a generalization to regular languages of simply typed $位$-terms, defined using denotational semantics in finite sets. We provide here some evidence for its robustness. First, we give an equivalent syntactic characterization that naturally extends the seminal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.00198v4-abstract-full').style.display = 'inline'; document.getElementById('2308.00198v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.00198v4-abstract-full" style="display: none;"> A fundamental theme in automata theory is regular languages of words and trees, and their many equivalent definitions. Salvati has proposed a generalization to regular languages of simply typed $位$-terms, defined using denotational semantics in finite sets. We provide here some evidence for its robustness. First, we give an equivalent syntactic characterization that naturally extends the seminal work of Hillebrand and Kanellakis connecting regular languages of words and syntactic $位$-definability. Second, we show that any finitary extensional model of the simply typed $位$-calculus, when used in Salvati's definition, recognizes exactly the same class of languages of $位$-terms as the category of finite sets does. The proofs of these two results rely on logical relations and can be seen as instances of a more general construction of a categorical nature, inspired by previous categorical accounts of logical relations using the gluing construction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.00198v4-abstract-full').style.display = 'none'; document.getElementById('2308.00198v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The proofs on "finitely pointable" CCCs in versions 1 and 2 were wrong; we now make slightly weaker claims on well-pointed locally finite CCCs. New in this version: added reference [3] and official DOI (proceedings of CSL 2024)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.15335">arXiv:2307.15335</a> <span> [<a href="https://arxiv.org/pdf/2307.15335">pdf</a>, <a href="https://arxiv.org/format/2307.15335">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> BARTPhoBEiT: Pre-trained Sequence-to-Sequence and Image Transformers Models for Vietnamese Visual Question Answering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+K+V">Khiem Vinh Tran</a>, <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+K">Kiet Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+N+L+T">Ngan Luu Thuy Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.15335v1-abstract-short" style="display: inline;"> Visual Question Answering (VQA) is an intricate and demanding task that integrates natural language processing (NLP) and computer vision (CV), capturing the interest of researchers. The English language, renowned for its wealth of resources, has witnessed notable advancements in both datasets and models designed for VQA. However, there is a lack of models that target specific countries such as Vie… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15335v1-abstract-full').style.display = 'inline'; document.getElementById('2307.15335v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.15335v1-abstract-full" style="display: none;"> Visual Question Answering (VQA) is an intricate and demanding task that integrates natural language processing (NLP) and computer vision (CV), capturing the interest of researchers. The English language, renowned for its wealth of resources, has witnessed notable advancements in both datasets and models designed for VQA. However, there is a lack of models that target specific countries such as Vietnam. To address this limitation, we introduce a transformer-based Vietnamese model named BARTPhoBEiT. This model includes pre-trained Sequence-to-Sequence and bidirectional encoder representation from Image Transformers in Vietnamese and evaluates Vietnamese VQA datasets. Experimental results demonstrate that our proposed model outperforms the strong baseline and improves the state-of-the-art in six metrics: Accuracy, Precision, Recall, F1-score, WUPS 0.0, and WUPS 0.9. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15335v1-abstract-full').style.display = 'none'; document.getElementById('2307.15335v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.11057">arXiv:2307.11057</a> <span> [<a href="https://arxiv.org/pdf/2307.11057">pdf</a>, <a href="https://arxiv.org/format/2307.11057">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Formal Languages and Automata Theory">cs.FL</span> </div> </div> <p class="title is-5 mathjax"> Two-way automata and transducers with planar behaviours are aperiodic </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a>, <a href="/search/cs?searchtype=author&query=No%C3%BBs%2C+C">Camille No没s</a>, <a href="/search/cs?searchtype=author&query=Pradic%2C+C">C茅cilia Pradic</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.11057v1-abstract-short" style="display: inline;"> We consider a notion of planarity for two-way finite automata and transducers, inspired by Temperley-Lieb monoids of planar diagrams. We show that this restriction captures star-free languages and first-order transductions. </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.11057v1-abstract-full" style="display: none;"> We consider a notion of planarity for two-way finite automata and transducers, inspired by Temperley-Lieb monoids of planar diagrams. We show that this restriction captures star-free languages and first-order transductions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.11057v1-abstract-full').style.display = 'none'; document.getElementById('2307.11057v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">18 pages, DMTCS submission</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.08798">arXiv:2306.08798</a> <span> [<a href="https://arxiv.org/pdf/2306.08798">pdf</a>, <a href="https://arxiv.org/format/2306.08798">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> MPSA-DenseNet: A novel deep learning model for English accent classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Song%2C+T">Tianyu Song</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T+H">Linh Thi Hoai Nguyen</a>, <a href="/search/cs?searchtype=author&query=Ta%2C+T+V">Ton Viet Ta</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.08798v1-abstract-short" style="display: inline;"> This paper presents three innovative deep learning models for English accent classification: Multi-DenseNet, PSA-DenseNet, and MPSE-DenseNet, that combine multi-task learning and the PSA module attention mechanism with DenseNet. We applied these models to data collected from six dialects of English across native English speaking regions (Britain, the United States, Scotland) and nonnative English… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.08798v1-abstract-full').style.display = 'inline'; document.getElementById('2306.08798v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.08798v1-abstract-full" style="display: none;"> This paper presents three innovative deep learning models for English accent classification: Multi-DenseNet, PSA-DenseNet, and MPSE-DenseNet, that combine multi-task learning and the PSA module attention mechanism with DenseNet. We applied these models to data collected from six dialects of English across native English speaking regions (Britain, the United States, Scotland) and nonnative English speaking regions (China, Germany, India). Our experimental results show a significant improvement in classification accuracy, particularly with MPSA-DenseNet, which outperforms all other models, including DenseNet and EPSA models previously used for accent identification. Our findings indicate that MPSA-DenseNet is a highly promising model for accurately identifying English accents. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.08798v1-abstract-full').style.display = 'none'; document.getElementById('2306.08798v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.19709">arXiv:2305.19709</a> <span> [<a href="https://arxiv.org/pdf/2305.19709">pdf</a>, <a href="https://arxiv.org/format/2305.19709">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Linh The Nguyen</a>, <a href="/search/cs?searchtype=author&query=Pham%2C+T">Thinh Pham</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D+Q">Dat Quoc Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.19709v1-abstract-short" style="display: inline;"> We present XPhoneBERT, the first multilingual model pre-trained to learn phoneme representations for the downstream text-to-speech (TTS) task. Our XPhoneBERT has the same model architecture as BERT-base, trained using the RoBERTa pre-training approach on 330M phoneme-level sentences from nearly 100 languages and locales. Experimental results show that employing XPhoneBERT as an input phoneme encod… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.19709v1-abstract-full').style.display = 'inline'; document.getElementById('2305.19709v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.19709v1-abstract-full" style="display: none;"> We present XPhoneBERT, the first multilingual model pre-trained to learn phoneme representations for the downstream text-to-speech (TTS) task. Our XPhoneBERT has the same model architecture as BERT-base, trained using the RoBERTa pre-training approach on 330M phoneme-level sentences from nearly 100 languages and locales. Experimental results show that employing XPhoneBERT as an input phoneme encoder significantly boosts the performance of a strong neural TTS model in terms of naturalness and prosody and also helps produce fairly high-quality speech with limited training data. We publicly release our pre-trained XPhoneBERT with the hope that it would facilitate future research and downstream TTS applications for multiple languages. Our XPhoneBERT model is available at https://github.com/VinAIResearch/XPhoneBERT <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.19709v1-abstract-full').style.display = 'none'; document.getElementById('2305.19709v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">In Proceedings of INTERSPEECH 2023 (to appear)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.12601">arXiv:2305.12601</a> <span> [<a href="https://arxiv.org/pdf/2305.12601">pdf</a>, <a href="https://arxiv.org/format/2305.12601">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Programming Languages">cs.PL</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.46298/lmcs-20(3:21)2024">10.46298/lmcs-20(3:21)2024 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Simply typed convertibility is TOWER-complete even for safe lambda-terms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.12601v4-abstract-short" style="display: inline;"> We consider the following decision problem: given two simply typed $位$-terms, are they $尾$-convertible? Equivalently, do they have the same normal form? It is famously non-elementary, but the precise complexity - namely TOWER-complete - is lesser known. One goal of this short paper is to popularize this fact. Our original contribution is to show that the problem stays TOWER-complete when the two… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.12601v4-abstract-full').style.display = 'inline'; document.getElementById('2305.12601v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.12601v4-abstract-full" style="display: none;"> We consider the following decision problem: given two simply typed $位$-terms, are they $尾$-convertible? Equivalently, do they have the same normal form? It is famously non-elementary, but the precise complexity - namely TOWER-complete - is lesser known. One goal of this short paper is to popularize this fact. Our original contribution is to show that the problem stays TOWER-complete when the two input terms belong to Blum and Ong's safe $位$-calculus, a fragment of the simply typed $位$-calculus arising from the study of higher-order recursion schemes. Previously, the best known lower bound for this safe $尾$-convertibility problem was PSPACE-hardness. Our proof proceeds by reduction from the star-free expression equivalence problem, taking inspiration from the author's work with Pradic on "implicit automata in typed $位$-calculi". These results also hold for $尾畏$-convertibility. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.12601v4-abstract-full').style.display = 'none'; document.getElementById('2305.12601v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Logical Methods in Computer Science, Volume 20, Issue 3 (September 5, 2024) lmcs:11344 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.06546">arXiv:2303.06546</a> <span> [<a href="https://arxiv.org/pdf/2303.06546">pdf</a>, <a href="https://arxiv.org/format/2303.06546">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Blockchain-Empowered Trustworthy Data Sharing: Fundamentals, Applications, and Challenges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Linh T. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+D">Lam Duc Nguyen</a>, <a href="/search/cs?searchtype=author&query=Hoang%2C+T">Thong Hoang</a>, <a href="/search/cs?searchtype=author&query=Bandara%2C+D">Dilum Bandara</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Q">Qin Wang</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Q">Qinghua Lu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+X">Xiwei Xu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+L">Liming Zhu</a>, <a href="/search/cs?searchtype=author&query=Popovski%2C+P">Petar Popovski</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+S">Shiping Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.06546v1-abstract-short" style="display: inline;"> Various data-sharing platforms have emerged with the growing public demand for open data and legislation mandating certain data to remain open. Most of these platforms remain opaque, leading to many questions about data accuracy, provenance and lineage, privacy implications, consent management, and the lack of fair incentives for data providers. With their transparency, immutability, non-repudiati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.06546v1-abstract-full').style.display = 'inline'; document.getElementById('2303.06546v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.06546v1-abstract-full" style="display: none;"> Various data-sharing platforms have emerged with the growing public demand for open data and legislation mandating certain data to remain open. Most of these platforms remain opaque, leading to many questions about data accuracy, provenance and lineage, privacy implications, consent management, and the lack of fair incentives for data providers. With their transparency, immutability, non-repudiation, and decentralization properties, blockchains could not be more apt to answer these questions and enhance trust in a data-sharing platform. However, blockchains are not good at handling the four Vs of big data (i.e., volume, variety, velocity, and veracity) due to their limited performance, scalability, and high cost. Given many related works proposes blockchain-based trustworthy data-sharing solutions, there is increasing confusion and difficulties in understanding and selecting these technologies and platforms in terms of their sharing mechanisms, sharing services, quality of services, and applications. In this paper, we conduct a comprehensive survey on blockchain-based data-sharing architectures and applications to fill the gap. First, we present the foundations of blockchains and discuss the challenges of current data-sharing techniques. Second, we focus on the convergence of blockchain and data sharing to give a clear picture of this landscape and propose a reference architecture for blockchain-based data sharing. Third, we discuss the industrial applications of blockchain-based data sharing, ranging from healthcare and smart grid to transportation and decarbonization. For each application, we provide lessons learned for the deployment of Blockchain-based data sharing. Finally, we discuss research challenges and open research directions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.06546v1-abstract-full').style.display = 'none'; document.getElementById('2303.06546v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">40 pages, 15 figures, and 8 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.05692">arXiv:2303.05692</a> <span> [<a href="https://arxiv.org/pdf/2303.05692">pdf</a>, <a href="https://arxiv.org/ps/2303.05692">ps</a>, <a href="https://arxiv.org/format/2303.05692">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Semantic-Preserving Augmentation for Robust Image-Text Retrieval </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sunwoo Kim</a>, <a href="/search/cs?searchtype=author&query=Shim%2C+K">Kyuhong Shim</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luong Trung Nguyen</a>, <a href="/search/cs?searchtype=author&query=Shim%2C+B">Byonghyo Shim</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.05692v1-abstract-short" style="display: inline;"> Image text retrieval is a task to search for the proper textual descriptions of the visual world and vice versa. One challenge of this task is the vulnerability to input image and text corruptions. Such corruptions are often unobserved during the training, and degrade the retrieval model decision quality substantially. In this paper, we propose a novel image text retrieval technique, referred to a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.05692v1-abstract-full').style.display = 'inline'; document.getElementById('2303.05692v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.05692v1-abstract-full" style="display: none;"> Image text retrieval is a task to search for the proper textual descriptions of the visual world and vice versa. One challenge of this task is the vulnerability to input image and text corruptions. Such corruptions are often unobserved during the training, and degrade the retrieval model decision quality substantially. In this paper, we propose a novel image text retrieval technique, referred to as robust visual semantic embedding (RVSE), which consists of novel image-based and text-based augmentation techniques called semantic preserving augmentation for image (SPAugI) and text (SPAugT). Since SPAugI and SPAugT change the original data in a way that its semantic information is preserved, we enforce the feature extractors to generate semantic aware embedding vectors regardless of the corruption, improving the model robustness significantly. From extensive experiments using benchmark datasets, we show that RVSE outperforms conventional retrieval schemes in terms of image-text retrieval performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.05692v1-abstract-full').style.display = 'none'; document.getElementById('2303.05692v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to ICASSP 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.09234">arXiv:2301.09234</a> <span> [<a href="https://arxiv.org/pdf/2301.09234">pdf</a>, <a href="https://arxiv.org/format/2301.09234">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Formal Languages and Automata Theory">cs.FL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> </div> </div> <p class="title is-5 mathjax"> Refutations of pebble minimization via output languages </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kiefer%2C+S">Sandra Kiefer</a>, <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a>, <a href="/search/cs?searchtype=author&query=Pradic%2C+C">C茅cilia Pradic</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2301.09234v2-abstract-short" style="display: inline;"> Polyregular functions are the class of string-to-string functions definable by pebble transducers, an extension of finite-state automata with outputs and multiple two-way reading heads (pebbles) with a stack discipline. If a polyregular function can be computed with $k$ pebbles, then its output length is bounded by a polynomial of degree $k$ in the input length. But Boja艅czyk has shown that the co… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.09234v2-abstract-full').style.display = 'inline'; document.getElementById('2301.09234v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.09234v2-abstract-full" style="display: none;"> Polyregular functions are the class of string-to-string functions definable by pebble transducers, an extension of finite-state automata with outputs and multiple two-way reading heads (pebbles) with a stack discipline. If a polyregular function can be computed with $k$ pebbles, then its output length is bounded by a polynomial of degree $k$ in the input length. But Boja艅czyk has shown that the converse fails. In this paper, we provide two alternative easier proofs. The first establishes by elementary means that some quadratic polyregular function requires 3 pebbles. The second proof - just as short, albeit less elementary - shows a stronger statement: for every $k$, there exists some polyregular function with quadratic growth whose output language differs from that of any $k$-fold composition of macro tree transducers (and which therefore cannot be computed by a $k$-pebble transducer). Along the way, we also refute a conjectured logical characterization of polyblind functions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.09234v2-abstract-full').style.display = 'none'; document.getElementById('2301.09234v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">20 pages, for submission to Fundamenta Informaticae; this version excludes some of the material in the v1, which may appear in other subsequent papers</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.10482">arXiv:2209.10482</a> <span> [<a href="https://arxiv.org/pdf/2209.10482">pdf</a>, <a href="https://arxiv.org/format/2209.10482">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> SMTCE: A Social Media Text Classification Evaluation Benchmark and BERTology Models for Vietnamese </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luan Thanh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+K">Kiet Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+N+L">Ngan Luu-Thuy Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2209.10482v1-abstract-short" style="display: inline;"> Text classification is a typical natural language processing or computational linguistics task with various interesting applications. As the number of users on social media platforms increases, data acceleration promotes emerging studies on Social Media Text Classification (SMTC) or social media text mining on these valuable resources. In contrast to English, Vietnamese, one of the low-resource la… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.10482v1-abstract-full').style.display = 'inline'; document.getElementById('2209.10482v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.10482v1-abstract-full" style="display: none;"> Text classification is a typical natural language processing or computational linguistics task with various interesting applications. As the number of users on social media platforms increases, data acceleration promotes emerging studies on Social Media Text Classification (SMTC) or social media text mining on these valuable resources. In contrast to English, Vietnamese, one of the low-resource languages, is still not concentrated on and exploited thoroughly. Inspired by the success of the GLUE, we introduce the Social Media Text Classification Evaluation (SMTCE) benchmark, as a collection of datasets and models across a diverse set of SMTC tasks. With the proposed benchmark, we implement and analyze the effectiveness of a variety of multilingual BERT-based models (mBERT, XLM-R, and DistilmBERT) and monolingual BERT-based models (PhoBERT, viBERT, vELECTRA, and viBERT4news) for tasks in the SMTCE benchmark. Monolingual models outperform multilingual models and achieve state-of-the-art results on all text classification tasks. It provides an objective assessment of multilingual and monolingual BERT-based models on the benchmark, which will benefit future studies about BERTology in the Vietnamese language. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.10482v1-abstract-full').style.display = 'none'; document.getElementById('2209.10482v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at The 36th annual Meeting of Pacific Asia Conference on Language, Information and Computation (PACLIC 36)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.07825">arXiv:2209.07825</a> <span> [<a href="https://arxiv.org/pdf/2209.07825">pdf</a>, <a href="https://arxiv.org/format/2209.07825">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.46298/lmcs-19(4:25)2023">10.46298/lmcs-19(4:25)2023 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A System of Interaction and Structure III: The Complexity of BV and Pomset Logic </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a>, <a href="/search/cs?searchtype=author&query=Stra%C3%9Fburger%2C+L">Lutz Stra脽burger</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2209.07825v5-abstract-short" style="display: inline;"> Pomset logic and BV are both logics that extend multiplicative linear logic (with Mix) with a third connective that is self-dual and non-commutative. Whereas pomset logic originates from the study of coherence spaces and proof nets, BV originates from the study of series-parallel orders, cographs, and proof systems. Both logics enjoy a cut-admissibility result, but for neither logic can this be do… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.07825v5-abstract-full').style.display = 'inline'; document.getElementById('2209.07825v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.07825v5-abstract-full" style="display: none;"> Pomset logic and BV are both logics that extend multiplicative linear logic (with Mix) with a third connective that is self-dual and non-commutative. Whereas pomset logic originates from the study of coherence spaces and proof nets, BV originates from the study of series-parallel orders, cographs, and proof systems. Both logics enjoy a cut-admissibility result, but for neither logic can this be done in the sequent calculus. Provability in pomset logic can be checked via a proof net correctness criterion and in BV via a deep inference proof system. It has long been conjectured that these two logics are the same. In this paper we show that this conjecture is false. We also investigate the complexity of the two logics, exhibiting a huge gap between the two. Whereas provability in BV is NP-complete, provability in pomset logic is $危_2^p$-complete. We also make some observations with respect to possible sequent systems for the two logics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.07825v5-abstract-full').style.display = 'none'; document.getElementById('2209.07825v5-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Logical Methods in Computer Science, Volume 19, Issue 4 (December 18, 2023) lmcs:10057 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.01304">arXiv:2209.01304</a> <span> [<a href="https://arxiv.org/pdf/2209.01304">pdf</a>, <a href="https://arxiv.org/format/2209.01304">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.25073/2588-1086/vnucsce.369">10.25073/2588-1086/vnucsce.369 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> vieCap4H-VLSP 2021: Vietnamese Image Captioning for Healthcare Domain using Swin Transformer and Attention-based LSTM </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+T">Thanh Tin Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+H">Long H. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Pham%2C+N+T">Nhat Truong Pham</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Liu Tai Nguyen</a>, <a href="/search/cs?searchtype=author&query=Do%2C+V+H">Van Huong Do</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H">Hai Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+N+D">Ngoc Duy Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2209.01304v1-abstract-short" style="display: inline;"> This study presents our approach on the automatic Vietnamese image captioning for healthcare domain in text processing tasks of Vietnamese Language and Speech Processing (VLSP) Challenge 2021, as shown in Figure 1. In recent years, image captioning often employs a convolutional neural network-based architecture as an encoder and a long short-term memory (LSTM) as a decoder to generate sentences. T… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.01304v1-abstract-full').style.display = 'inline'; document.getElementById('2209.01304v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.01304v1-abstract-full" style="display: none;"> This study presents our approach on the automatic Vietnamese image captioning for healthcare domain in text processing tasks of Vietnamese Language and Speech Processing (VLSP) Challenge 2021, as shown in Figure 1. In recent years, image captioning often employs a convolutional neural network-based architecture as an encoder and a long short-term memory (LSTM) as a decoder to generate sentences. These models perform remarkably well in different datasets. Our proposed model also has an encoder and a decoder, but we instead use a Swin Transformer in the encoder, and a LSTM combined with an attention module in the decoder. The study presents our training experiments and techniques used during the competition. Our model achieves a BLEU4 score of 0.293 on the vietCap4H dataset, and the score is ranked the 3$^{rd}$ place on the private leaderboard. Our code can be found at \url{https://git.io/JDdJm}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.01304v1-abstract-full').style.display = 'none'; document.getElementById('2209.01304v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for publication in the VNU Journal of Science: Computer Science and Communication Engineering</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> VNU Journal of Science: Computer Science and Communication Engineering, 38(2), 2022 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.04243">arXiv:2208.04243</a> <span> [<a href="https://arxiv.org/pdf/2208.04243">pdf</a>, <a href="https://arxiv.org/format/2208.04243">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> A High-Quality and Large-Scale Dataset for English-Vietnamese Speech Translation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Linh The Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+L">Nguyen Luong Tran</a>, <a href="/search/cs?searchtype=author&query=Doan%2C+L">Long Doan</a>, <a href="/search/cs?searchtype=author&query=Luong%2C+M">Manh Luong</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D+Q">Dat Quoc Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2208.04243v1-abstract-short" style="display: inline;"> In this paper, we introduce a high-quality and large-scale benchmark dataset for English-Vietnamese speech translation with 508 audio hours, consisting of 331K triplets of (sentence-lengthed audio, English source transcript sentence, Vietnamese target subtitle sentence). We also conduct empirical experiments using strong baselines and find that the traditional "Cascaded" approach still outperforms… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.04243v1-abstract-full').style.display = 'inline'; document.getElementById('2208.04243v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.04243v1-abstract-full" style="display: none;"> In this paper, we introduce a high-quality and large-scale benchmark dataset for English-Vietnamese speech translation with 508 audio hours, consisting of 331K triplets of (sentence-lengthed audio, English source transcript sentence, Vietnamese target subtitle sentence). We also conduct empirical experiments using strong baselines and find that the traditional "Cascaded" approach still outperforms the modern "End-to-End" approach. To the best of our knowledge, this is the first large-scale English-Vietnamese speech translation study. We hope both our publicly available dataset and study can serve as a starting point for future research and applications on English-Vietnamese speech translation. Our dataset is available at https://github.com/VinAIResearch/PhoST <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.04243v1-abstract-full').style.display = 'none'; document.getElementById('2208.04243v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">In Proceedings of INTERSPEECH 2022, to appear. The first three authors contributed equally to this work</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2206.09600">arXiv:2206.09600</a> <span> [<a href="https://arxiv.org/pdf/2206.09600">pdf</a>, <a href="https://arxiv.org/format/2206.09600">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> SPBERTQA: A Two-Stage Question Answering System Based on Sentence Transformers for Medical Texts </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+N+T">Nhung Thi-Hong Nguyen</a>, <a href="/search/cs?searchtype=author&query=Ha%2C+P+P">Phuong Phan-Dieu Ha</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luan Thanh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+K">Kiet Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+N+L">Ngan Luu-Thuy Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2206.09600v1-abstract-short" style="display: inline;"> Question answering (QA) systems have gained explosive attention in recent years. However, QA tasks in Vietnamese do not have many datasets. Significantly, there is mostly no dataset in the medical domain. Therefore, we built a Vietnamese Healthcare Question Answering dataset (ViHealthQA), including 10,015 question-answer passage pairs for this task, in which questions from health-interested users… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.09600v1-abstract-full').style.display = 'inline'; document.getElementById('2206.09600v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2206.09600v1-abstract-full" style="display: none;"> Question answering (QA) systems have gained explosive attention in recent years. However, QA tasks in Vietnamese do not have many datasets. Significantly, there is mostly no dataset in the medical domain. Therefore, we built a Vietnamese Healthcare Question Answering dataset (ViHealthQA), including 10,015 question-answer passage pairs for this task, in which questions from health-interested users were asked on prestigious health websites and answers from highly qualified experts. This paper proposes a two-stage QA system based on Sentence-BERT (SBERT) using multiple negatives ranking (MNR) loss combined with BM25. Then, we conduct diverse experiments with many bag-of-words models to assess our system's performance. With the obtained results, this system achieves better performance than traditional methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.09600v1-abstract-full').style.display = 'none'; document.getElementById('2206.09600v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.11400">arXiv:2203.11400</a> <span> [<a href="https://arxiv.org/pdf/2203.11400">pdf</a>, <a href="https://arxiv.org/format/2203.11400">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.25073/2588-1086/vnucsce.340">10.25073/2588-1086/vnucsce.340 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> VLSP 2021 - ViMRC Challenge: Vietnamese Machine Reading Comprehension </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+K">Kiet Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+S+Q">Son Quoc Tran</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luan Thanh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Van+Huynh%2C+T">Tin Van Huynh</a>, <a href="/search/cs?searchtype=author&query=Luu%2C+S+T">Son T. Luu</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+N+L">Ngan Luu-Thuy Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2203.11400v3-abstract-short" style="display: inline;"> One of the emerging research trends in natural language understanding is machine reading comprehension (MRC) which is the task to find answers to human questions based on textual data. Existing Vietnamese datasets for MRC research concentrate solely on answerable questions. However, in reality, questions can be unanswerable for which the correct answer is not stated in the given textual data. To a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.11400v3-abstract-full').style.display = 'inline'; document.getElementById('2203.11400v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.11400v3-abstract-full" style="display: none;"> One of the emerging research trends in natural language understanding is machine reading comprehension (MRC) which is the task to find answers to human questions based on textual data. Existing Vietnamese datasets for MRC research concentrate solely on answerable questions. However, in reality, questions can be unanswerable for which the correct answer is not stated in the given textual data. To address the weakness, we provide the research community with a benchmark dataset named UIT-ViQuAD 2.0 for evaluating the MRC task and question answering systems for the Vietnamese language. We use UIT-ViQuAD 2.0 as a benchmark dataset for the challenge on Vietnamese MRC at the Eighth Workshop on Vietnamese Language and Speech Processing (VLSP 2021). This task attracted 77 participant teams from 34 universities and other organizations. In this article, we present details of the organization of the challenge, an overview of the methods employed by shared-task participants, and the results. The highest performances are 77.24% in F1-score and 67.43% in Exact Match on the private test set. The Vietnamese MRC systems proposed by the top 3 teams use XLM-RoBERTa, a powerful pre-trained language model based on the transformer architecture. The UIT-ViQuAD 2.0 dataset motivates researchers to further explore the Vietnamese machine reading comprehension task and related tasks such as question answering, question generation, and natural language inference. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.11400v3-abstract-full').style.display = 'none'; document.getElementById('2203.11400v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The 8th International Workshop on Vietnamese Language and Speech Processing (VLSP 2021)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2110.12199">arXiv:2110.12199</a> <span> [<a href="https://arxiv.org/pdf/2110.12199">pdf</a>, <a href="https://arxiv.org/format/2110.12199">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine Translation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Doan%2C+L">Long Doan</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Linh The Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+L">Nguyen Luong Tran</a>, <a href="/search/cs?searchtype=author&query=Hoang%2C+T">Thai Hoang</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D+Q">Dat Quoc Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2110.12199v1-abstract-short" style="display: inline;"> We introduce a high-quality and large-scale Vietnamese-English parallel dataset of 3.02M sentence pairs, which is 2.9M pairs larger than the benchmark Vietnamese-English machine translation corpus IWSLT15. We conduct experiments comparing strong neural baselines and well-known automatic translation engines on our dataset and find that in both automatic and human evaluations: the best performance i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.12199v1-abstract-full').style.display = 'inline'; document.getElementById('2110.12199v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.12199v1-abstract-full" style="display: none;"> We introduce a high-quality and large-scale Vietnamese-English parallel dataset of 3.02M sentence pairs, which is 2.9M pairs larger than the benchmark Vietnamese-English machine translation corpus IWSLT15. We conduct experiments comparing strong neural baselines and well-known automatic translation engines on our dataset and find that in both automatic and human evaluations: the best performance is obtained by fine-tuning the pre-trained sequence-to-sequence denoising auto-encoder mBART. To our best knowledge, this is the first large-scale Vietnamese-English machine translation study. We hope our publicly available dataset and study can serve as a starting point for future research and applications on Vietnamese-English machine translation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.12199v1-abstract-full').style.display = 'none'; document.getElementById('2110.12199v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To appear in Proceedings of EMNLP 2021 (main conference). The first three authors contribute equally to this work</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2110.05178">arXiv:2110.05178</a> <span> [<a href="https://arxiv.org/pdf/2110.05178">pdf</a>, <a href="https://arxiv.org/format/2110.05178">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TSP.2021.3125137">10.1109/TSP.2021.3125137 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Gradual Federated Learning with Simulated Annealing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luong Trung Nguyen</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J">Junhan Kim</a>, <a href="/search/cs?searchtype=author&query=Shim%2C+B">Byonghyo Shim</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2110.05178v1-abstract-short" style="display: inline;"> Federated averaging (FedAvg) is a popular federated learning (FL) technique that updates the global model by averaging local models and then transmits the updated global model to devices for their local model update. One main limitation of FedAvg is that the average-based global model is not necessarily better than local models in the early stage of the training process so that FedAvg might diverg… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.05178v1-abstract-full').style.display = 'inline'; document.getElementById('2110.05178v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.05178v1-abstract-full" style="display: none;"> Federated averaging (FedAvg) is a popular federated learning (FL) technique that updates the global model by averaging local models and then transmits the updated global model to devices for their local model update. One main limitation of FedAvg is that the average-based global model is not necessarily better than local models in the early stage of the training process so that FedAvg might diverge in realistic scenarios, especially when the data is non-identically distributed across devices and the number of data samples varies significantly from device to device. In this paper, we propose a new FL technique based on simulated annealing. The key idea of the proposed technique, henceforth referred to as \textit{simulated annealing-based FL} (SAFL), is to allow a device to choose its local model when the global model is immature. Specifically, by exploiting the simulated annealing strategy, we make each device choose its local model with high probability in early iterations when the global model is immature. From extensive numerical experiments using various benchmark datasets, we demonstrate that SAFL outperforms the conventional FedAvg technique in terms of the convergence speed and the classification accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.05178v1-abstract-full').style.display = 'none'; document.getElementById('2110.05178v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.03219">arXiv:2109.03219</a> <span> [<a href="https://arxiv.org/pdf/2109.03219">pdf</a>, <a href="https://arxiv.org/format/2109.03219">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Fruit-CoV: An Efficient Vision-based Framework for Speedy Detection and Diagnosis of SARS-CoV-2 Infections Through Recorded Cough Sounds </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+H">Long H. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Pham%2C+N+T">Nhat Truong Pham</a>, <a href="/search/cs?searchtype=author&query=Do%2C+V+H">Van Huong Do</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Liu Tai Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+T">Thanh Tin Nguyen</a>, <a href="/search/cs?searchtype=author&query=Do%2C+V+D">Van Dung Do</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H">Hai Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+N+D">Ngoc Duy Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2109.03219v1-abstract-short" style="display: inline;"> SARS-CoV-2 is colloquially known as COVID-19 that had an initial outbreak in December 2019. The deadly virus has spread across the world, taking part in the global pandemic disease since March 2020. In addition, a recent variant of SARS-CoV-2 named Delta is intractably contagious and responsible for more than four million deaths over the world. Therefore, it is vital to possess a self-testing serv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.03219v1-abstract-full').style.display = 'inline'; document.getElementById('2109.03219v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.03219v1-abstract-full" style="display: none;"> SARS-CoV-2 is colloquially known as COVID-19 that had an initial outbreak in December 2019. The deadly virus has spread across the world, taking part in the global pandemic disease since March 2020. In addition, a recent variant of SARS-CoV-2 named Delta is intractably contagious and responsible for more than four million deaths over the world. Therefore, it is vital to possess a self-testing service of SARS-CoV-2 at home. In this study, we introduce Fruit-CoV, a two-stage vision framework, which is capable of detecting SARS-CoV-2 infections through recorded cough sounds. Specifically, we convert sounds into Log-Mel Spectrograms and use the EfficientNet-V2 network to extract its visual features in the first stage. In the second stage, we use 14 convolutional layers extracted from the large-scale Pretrained Audio Neural Networks for audio pattern recognition (PANNs) and the Wavegram-Log-Mel-CNN to aggregate feature representations of the Log-Mel Spectrograms. Finally, we use the combined features to train a binary classifier. In this study, we use a dataset provided by the AICovidVN 115M Challenge, which includes a total of 7371 recorded cough sounds collected throughout Vietnam, India, and Switzerland. Experimental results show that our proposed model achieves an AUC score of 92.8% and ranks the 1st place on the leaderboard of the AICovidVN Challenge. More importantly, our proposed framework can be integrated into a call center or a VoIP system to speed up detecting SARS-CoV-2 infections through online/recorded cough sounds. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.03219v1-abstract-full').style.display = 'none'; document.getElementById('2109.03219v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">4 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2105.15079">arXiv:2105.15079</a> <span> [<a href="https://arxiv.org/pdf/2105.15079">pdf</a>, <a href="https://arxiv.org/format/2105.15079">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> SA2SL: From Aspect-Based Sentiment Analysis to Social Listening System for Business Intelligence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Phan%2C+L+L">Luong Luc Phan</a>, <a href="/search/cs?searchtype=author&query=Pham%2C+P+H">Phuc Huynh Pham</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+K+T">Kim Thi-Thanh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+T">Tham Thi Nguyen</a>, <a href="/search/cs?searchtype=author&query=Huynh%2C+S+K">Sieu Khai Huynh</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luan Thanh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Van+Huynh%2C+T">Tin Van Huynh</a>, <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+K">Kiet Van Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2105.15079v2-abstract-short" style="display: inline;"> In this paper, we present a process of building a social listening system based on aspect-based sentiment analysis in Vietnamese from creating a dataset to building a real application. Firstly, we create UIT-ViSFD, a Vietnamese Smartphone Feedback Dataset as a new benchmark corpus built based on a strict annotation schemes for evaluating aspect-based sentiment analysis, consisting of 11,122 human-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.15079v2-abstract-full').style.display = 'inline'; document.getElementById('2105.15079v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2105.15079v2-abstract-full" style="display: none;"> In this paper, we present a process of building a social listening system based on aspect-based sentiment analysis in Vietnamese from creating a dataset to building a real application. Firstly, we create UIT-ViSFD, a Vietnamese Smartphone Feedback Dataset as a new benchmark corpus built based on a strict annotation schemes for evaluating aspect-based sentiment analysis, consisting of 11,122 human-annotated comments for mobile e-commerce, which is freely available for research purposes. We also present a proposed approach based on the Bi-LSTM architecture with the fastText word embeddings for the Vietnamese aspect based sentiment task. Our experiments show that our approach achieves the best performances with the F1-score of 84.48% for the aspect task and 63.06% for the sentiment task, which performs several conventional machine learning and deep learning systems. Last but not least, we build SA2SL, a social listening system based on the best performance model on our dataset, which will inspire more social listening systems in future. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.15079v2-abstract-full').style.display = 'none'; document.getElementById('2105.15079v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 May, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2105.08358">arXiv:2105.08358</a> <span> [<a href="https://arxiv.org/pdf/2105.08358">pdf</a>, <a href="https://arxiv.org/format/2105.08358">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Formal Languages and Automata Theory">cs.FL</span> </div> </div> <p class="title is-5 mathjax"> Comparison-free polyregular functions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D+T">L锚 Th脿nh D农ng Tito Nguy锚n</a>, <a href="/search/cs?searchtype=author&query=No%C3%BBs%2C+C">Camille No没s</a>, <a href="/search/cs?searchtype=author&query=Pradic%2C+C">C茅cilia Pradic</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2105.08358v2-abstract-short" style="display: inline;"> This paper introduces a new automata-theoretic class of string-to-string functions with polynomial growth. Several equivalent definitions are provided: a machine model which is a restricted variant of pebble transducers, and a few inductive definitions that close the class of regular functions under certain operations. Our motivation for studying this class comes from another characterization, whi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.08358v2-abstract-full').style.display = 'inline'; document.getElementById('2105.08358v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2105.08358v2-abstract-full" style="display: none;"> This paper introduces a new automata-theoretic class of string-to-string functions with polynomial growth. Several equivalent definitions are provided: a machine model which is a restricted variant of pebble transducers, and a few inductive definitions that close the class of regular functions under certain operations. Our motivation for studying this class comes from another characterization, which we merely mention here but prove elsewhere, based on a $位$-calculus with a linear type system.As their name suggests, these comparison-free polyregular functions form a subclass of polyregular functions; we prove that the inclusion is strict. We also show that they are incomparable with HDT0L transductions, closed under usual function composition -- but not under a certain ``map'' combinator -- and satisfy a comparison-free version of the pebble minimization theorem.On the broader topic of polynomial growth transductions, we also consider the recently introduced layered streaming string transducers (SSTs), or equivalently k-marble transducers. We prove that a function can be obtained by composing such transducers together if and only if it is polyregular, and that k-layered SSTs (or k-marble transducers) are closed under ``map'' and equivalent to a corresponding notion of (k+1)-layered HDT0L systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.08358v2-abstract-full').style.display = 'none'; document.getElementById('2105.08358v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 May, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> International Colloquium on Automata, Languages and Programming 2021, Jul 2021, Glasgow, United Kingdom </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2104.11969">arXiv:2104.11969</a> <span> [<a href="https://arxiv.org/pdf/2104.11969">pdf</a>, <a href="https://arxiv.org/ps/2104.11969">ps</a>, <a href="https://arxiv.org/format/2104.11969">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Vietnamese Complaint Detection on E-Commerce Websites </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+N+T">Nhung Thi-Hong Nguyen</a>, <a href="/search/cs?searchtype=author&query=Ha%2C+P+P">Phuong Phan-Dieu Ha</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luan Thanh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+K">Kiet Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+N+L">Ngan Luu-Thuy Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2104.11969v3-abstract-short" style="display: inline;"> Customer product reviews play a role in improving the quality of products and services for business organizations or their brands. Complaining is an attitude that expresses dissatisfaction with an event or a product not meeting customer expectations. In this paper, we build a Open-domain Complaint Detection dataset (UIT-ViOCD), including 5,485 human-annotated reviews on four categories about produ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.11969v3-abstract-full').style.display = 'inline'; document.getElementById('2104.11969v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2104.11969v3-abstract-full" style="display: none;"> Customer product reviews play a role in improving the quality of products and services for business organizations or their brands. Complaining is an attitude that expresses dissatisfaction with an event or a product not meeting customer expectations. In this paper, we build a Open-domain Complaint Detection dataset (UIT-ViOCD), including 5,485 human-annotated reviews on four categories about product reviews on e-commerce sites. After the data collection phase, we proceed to the annotation task and achieve the inter-annotator agreement Am of 87%. Then, we present an extensive methodology for the research purposes and achieve 92.16% by F1-score for identifying complaints. With the results, in the future, we aim to build a system for open-domain complaint detection in E-commerce websites. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.11969v3-abstract-full').style.display = 'none'; document.getElementById('2104.11969v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2104.07376">arXiv:2104.07376</a> <span> [<a href="https://arxiv.org/pdf/2104.07376">pdf</a>, <a href="https://arxiv.org/format/2104.07376">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> UIT-E10dot3 at SemEval-2021 Task 5: Toxic Spans Detection with Named Entity Recognition and Question-Answering Approaches </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hoang%2C+P+G">Phu Gia Hoang</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luan Thanh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+K">Kiet Van Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2104.07376v1-abstract-short" style="display: inline;"> The increment of toxic comments on online space is causing tremendous effects on other vulnerable users. For this reason, considerable efforts are made to deal with this, and SemEval-2021 Task 5: Toxic Spans Detection is one of those. This task asks competitors to extract spans that have toxicity from the given texts, and we have done several analyses to understand its structure before doing exper… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.07376v1-abstract-full').style.display = 'inline'; document.getElementById('2104.07376v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2104.07376v1-abstract-full" style="display: none;"> The increment of toxic comments on online space is causing tremendous effects on other vulnerable users. For this reason, considerable efforts are made to deal with this, and SemEval-2021 Task 5: Toxic Spans Detection is one of those. This task asks competitors to extract spans that have toxicity from the given texts, and we have done several analyses to understand its structure before doing experiments. We solve this task by two approaches, Named Entity Recognition with spaCy library and Question-Answering with RoBERTa combining with ToxicBERT, and the former gains the highest F1-score of 66.99%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.07376v1-abstract-full').style.display = 'none'; document.getElementById('2104.07376v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at SemEval-2021 Task 5: Toxic Spans Detection, ACL-IJCNLP 2021</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.10069">arXiv:2103.10069</a> <span> [<a href="https://arxiv.org/pdf/2103.10069">pdf</a>, <a href="https://arxiv.org/format/2103.10069">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1007/978-3-030-79457-6_49">10.1007/978-3-030-79457-6_49 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Constructive and Toxic Speech Detection for Open-domain Social Media Comments in Vietnamese </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luan Thanh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+K">Kiet Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+N+L">Ngan Luu-Thuy Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2103.10069v5-abstract-short" style="display: inline;"> The rise of social media has led to the increasing of comments on online forums. However, there still exists invalid comments which are not informative for users. Moreover, those comments are also quite toxic and harmful to people. In this paper, we create a dataset for constructive and toxic speech detection, named UIT-ViCTSD (Vietnamese Constructive and Toxic Speech Detection dataset) with 10,00… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.10069v5-abstract-full').style.display = 'inline'; document.getElementById('2103.10069v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.10069v5-abstract-full" style="display: none;"> The rise of social media has led to the increasing of comments on online forums. However, there still exists invalid comments which are not informative for users. Moreover, those comments are also quite toxic and harmful to people. In this paper, we create a dataset for constructive and toxic speech detection, named UIT-ViCTSD (Vietnamese Constructive and Toxic Speech Detection dataset) with 10,000 human-annotated comments. For these tasks, we propose a system for constructive and toxic speech detection with the state-of-the-art transfer learning model in Vietnamese NLP as PhoBERT. With this system, we obtain F1-scores of 78.59% and 59.40% for classifying constructive and toxic comments, respectively. Besides, we implement various baseline models as traditional Machine Learning and Deep Neural Network-Based models to evaluate the dataset. With the results, we can solve several tasks on the online discussions and develop the framework for identifying constructiveness and toxicity of Vietnamese social media comments automatically. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.10069v5-abstract-full').style.display = 'none'; document.getElementById('2103.10069v5-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">IEA/AIE 2021: Advances and Trends in Artificial Intelligence. Artificial Intelligence Practices pp 572-583</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.01476">arXiv:2101.01476</a> <span> [<a href="https://arxiv.org/pdf/2101.01476">pdf</a>, <a href="https://arxiv.org/format/2101.01476">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> PhoNLP: A joint multi-task learning model for Vietnamese part-of-speech tagging, named entity recognition and dependency parsing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Linh The Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D+Q">Dat Quoc Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2101.01476v2-abstract-short" style="display: inline;"> We present the first multi-task learning model -- named PhoNLP -- for joint Vietnamese part-of-speech (POS) tagging, named entity recognition (NER) and dependency parsing. Experiments on Vietnamese benchmark datasets show that PhoNLP produces state-of-the-art results, outperforming a single-task learning approach that fine-tunes the pre-trained Vietnamese language model PhoBERT (Nguyen and Nguyen,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.01476v2-abstract-full').style.display = 'inline'; document.getElementById('2101.01476v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.01476v2-abstract-full" style="display: none;"> We present the first multi-task learning model -- named PhoNLP -- for joint Vietnamese part-of-speech (POS) tagging, named entity recognition (NER) and dependency parsing. Experiments on Vietnamese benchmark datasets show that PhoNLP produces state-of-the-art results, outperforming a single-task learning approach that fine-tunes the pre-trained Vietnamese language model PhoBERT (Nguyen and Nguyen, 2020) for each task independently. We publicly release PhoNLP as an open-source toolkit under the Apache License 2.0. Although we specify PhoNLP for Vietnamese, our PhoNLP training and evaluation command scripts in fact can directly work for other languages that have a pre-trained BERT-based language model and gold annotated corpora available for the three tasks of POS tagging, NER and dependency parsing. We hope that PhoNLP can serve as a strong baseline and useful toolkit for future NLP research and applications to not only Vietnamese but also the other languages. Our PhoNLP is available at: https://github.com/VinAIResearch/PhoNLP <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.01476v2-abstract-full').style.display = 'none'; document.getElementById('2101.01476v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To appear in Proceedings of NAACL 2021: Demonstrations</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2010.08232">arXiv:2010.08232</a> <span> [<a href="https://arxiv.org/pdf/2010.08232">pdf</a>, <a href="https://arxiv.org/format/2010.08232">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> WNUT-2020 Task 2: Identification of Informative COVID-19 English Tweets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+D+Q">Dat Quoc Nguyen</a>, <a href="/search/cs?searchtype=author&query=Vu%2C+T">Thanh Vu</a>, <a href="/search/cs?searchtype=author&query=Rahimi%2C+A">Afshin Rahimi</a>, <a href="/search/cs?searchtype=author&query=Dao%2C+M+H">Mai Hoang Dao</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Linh The Nguyen</a>, <a href="/search/cs?searchtype=author&query=Doan%2C+L">Long Doan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2010.08232v1-abstract-short" style="display: inline;"> In this paper, we provide an overview of the WNUT-2020 shared task on the identification of informative COVID-19 English Tweets. We describe how we construct a corpus of 10K Tweets and organize the development and evaluation phases for this task. In addition, we also present a brief summary of results obtained from the final system evaluation submissions of 55 teams, finding that (i) many systems… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.08232v1-abstract-full').style.display = 'inline'; document.getElementById('2010.08232v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.08232v1-abstract-full" style="display: none;"> In this paper, we provide an overview of the WNUT-2020 shared task on the identification of informative COVID-19 English Tweets. We describe how we construct a corpus of 10K Tweets and organize the development and evaluation phases for this task. In addition, we also present a brief summary of results obtained from the final system evaluation submissions of 55 teams, finding that (i) many systems obtain very high performance, up to 0.91 F1 score, (ii) the majority of the submissions achieve substantially higher results than the baseline fastText (Joulin et al., 2017), and (iii) fine-tuning pre-trained language models on relevant language data followed by supervised training performs well in this task. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.08232v1-abstract-full').style.display = 'none'; document.getElementById('2010.08232v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">In Proceedings of the 6th Workshop on Noisy User-generated Text</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2009.02671">arXiv:2009.02671</a> <span> [<a href="https://arxiv.org/pdf/2009.02671">pdf</a>, <a href="https://arxiv.org/format/2009.02671">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.18653/v1/2020.wnut-1.50">10.18653/v1/2020.wnut-1.50 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> BANANA at WNUT-2020 Task 2: Identifying COVID-19 Information on Twitter by Combining Deep Learning and Transfer Learning Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Van+Huynh%2C+T">Tin Van Huynh</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luan Thanh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Luu%2C+S+T">Son T. Luu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2009.02671v2-abstract-short" style="display: inline;"> The outbreak COVID-19 virus caused a significant impact on the health of people all over the world. Therefore, it is essential to have a piece of constant and accurate information about the disease with everyone. This paper describes our prediction system for WNUT-2020 Task 2: Identification of Informative COVID-19 English Tweets. The dataset for this task contains size 10,000 tweets in English la… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.02671v2-abstract-full').style.display = 'inline'; document.getElementById('2009.02671v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.02671v2-abstract-full" style="display: none;"> The outbreak COVID-19 virus caused a significant impact on the health of people all over the world. Therefore, it is essential to have a piece of constant and accurate information about the disease with everyone. This paper describes our prediction system for WNUT-2020 Task 2: Identification of Informative COVID-19 English Tweets. The dataset for this task contains size 10,000 tweets in English labeled by humans. The ensemble model from our three transformer and deep learning models is used for the final prediction. The experimental result indicates that we have achieved F1 for the INFORMATIVE label on our systems at 88.81% on the test set. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.02671v2-abstract-full').style.display = 'none'; document.getElementById('2009.02671v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 September, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to 2020 The 6th Workshop on Noisy User-generated Text (W-NUT)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2008.01050">arXiv:2008.01050</a> <span> [<a href="https://arxiv.org/pdf/2008.01050">pdf</a>, <a href="https://arxiv.org/format/2008.01050">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Formal Languages and Automata Theory">cs.FL</span> </div> </div> <p class="title is-5 mathjax"> Implicit automata in typed $位$-calculi II: streaming transducers vs categorical semantics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a>, <a href="/search/cs?searchtype=author&query=No%C3%BBs%2C+C">Camille No没s</a>, <a href="/search/cs?searchtype=author&query=Pradic%2C+C">C茅cilia Pradic</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2008.01050v3-abstract-short" style="display: inline;"> We characterize regular string transductions as programs in a linear $位$-calculus with additives. One direction of this equivalence is proved by encoding copyless streaming string transducers (SSTs), which compute regular functions, into our $位$-calculus. For the converse, we consider a categorical framework for defining automata and transducers over words, which allows us to relate register upd… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.01050v3-abstract-full').style.display = 'inline'; document.getElementById('2008.01050v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2008.01050v3-abstract-full" style="display: none;"> We characterize regular string transductions as programs in a linear $位$-calculus with additives. One direction of this equivalence is proved by encoding copyless streaming string transducers (SSTs), which compute regular functions, into our $位$-calculus. For the converse, we consider a categorical framework for defining automata and transducers over words, which allows us to relate register updates in SSTs to the semantics of the linear $位$-calculus in a suitable monoidal closed category. To illustrate the relevance of monoidal closure to automata theory, we also leverage this notion to give abstract generalizations of the arguments showing that copyless SSTs may be determinized and that the composition of two regular functions may be implemented by a copyless SST. Our main result is then generalized from strings to trees using a similar approach. In doing so, we exhibit a connection between a feature of streaming tree transducers and the multiplicative/additive distinction of linear logic. Keywords: MSO transductions, implicit complexity, Dialectica categories, Church encodings <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.01050v3-abstract-full').style.display = 'none'; document.getElementById('2008.01050v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">108 pages, 23 figures. Theorem 3.53 was wrong in previous versions. This is corrected and a more detailed proof is provided in a new appendix. Miscellaneous minor typos were also corrected</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 03B40; 03B70; 68Q45 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> F.4.1; F.4.3 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1912.12804">arXiv:1912.12804</a> <span> [<a href="https://arxiv.org/pdf/1912.12804">pdf</a>, <a href="https://arxiv.org/ps/1912.12804">ps</a>, <a href="https://arxiv.org/format/1912.12804">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Joint Sparse Recovery Using Signal Space Matching Pursuit </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kim%2C+J">Junhan Kim</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jian Wang</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luong Trung Nguyen</a>, <a href="/search/cs?searchtype=author&query=Shim%2C+B">Byonghyo Shim</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1912.12804v2-abstract-short" style="display: inline;"> In this paper, we put forth a new joint sparse recovery algorithm called signal space matching pursuit (SSMP). The key idea of the proposed SSMP algorithm is to sequentially investigate the support of jointly sparse vectors to minimize the subspace distance to the residual space. Our performance guarantee analysis indicates that SSMP accurately reconstructs any row $K$-sparse matrix of rank $r$ in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.12804v2-abstract-full').style.display = 'inline'; document.getElementById('1912.12804v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1912.12804v2-abstract-full" style="display: none;"> In this paper, we put forth a new joint sparse recovery algorithm called signal space matching pursuit (SSMP). The key idea of the proposed SSMP algorithm is to sequentially investigate the support of jointly sparse vectors to minimize the subspace distance to the residual space. Our performance guarantee analysis indicates that SSMP accurately reconstructs any row $K$-sparse matrix of rank $r$ in the full row rank scenario if the sampling matrix $\mathbf{A}$ satisfies $\text{krank}(\mathbf{A}) \ge K+1$, which meets the fundamental minimum requirement on $\mathbf{A}$ to ensure exact recovery. We also show that SSMP guarantees exact reconstruction in at most $K-r+\lceil \frac{r}{L} \rceil$ iterations, provided that $\mathbf{A}$ satisfies the restricted isometry property (RIP) of order $L(K-r)+r+1$ with $$未_{L(K-r)+r+1} < \max \left \{ \frac{\sqrt{r}}{\sqrt{K+\frac{r}{4}}+\sqrt{\frac{r}{4}}}, \frac{\sqrt{L}}{\sqrt{K}+1.15 \sqrt{L}} \right \},$$ where $L$ is the number of indices chosen in each iteration. This implies that the requirement on the RIP constant becomes less restrictive when $r$ increases. Such behavior seems to be natural but has not been reported for most of conventional methods. We further show that if $r=1$, then by running more than $K$ iterations, the performance guarantee of SSMP can be improved to $未_{\lfloor 7.8K \rfloor} \le 0.155$. In addition, we show that under a suitable RIP condition, the reconstruction error of SSMP is upper bounded by a constant multiple of the noise power, which demonstrates the stability of SSMP under measurement noise. Finally, from extensive numerical experiments, we show that SSMP outperforms conventional joint sparse recovery algorithms both in noiseless and noisy scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.12804v2-abstract-full').style.display = 'none'; document.getElementById('1912.12804v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 March, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1912.10606">arXiv:1912.10606</a> <span>  </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> </div> </div> <p class="title is-5 mathjax"> Complexity of correctness for pomset logic proof nets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1912.10606v4-abstract-short" style="display: inline;"> We show that it is coNP-complete to decide whether a given proof structure of pomset logic is a correct proof net, using the graph-theoretic used in a previous paper of ours (arXiv:1901.10247). </span> <span class="abstract-full has-text-grey-dark mathjax" id="1912.10606v4-abstract-full" style="display: none;"> We show that it is coNP-complete to decide whether a given proof structure of pomset logic is a correct proof net, using the graph-theoretic used in a previous paper of ours (arXiv:1901.10247). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.10606v4-abstract-full').style.display = 'none'; document.getElementById('1912.10606v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Fully subsumed by arXiv:2209.07825 (which contains a lot more material and has an additional coauthor)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> F.4.1 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> F.4.1 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1909.03542">arXiv:1909.03542</a> <span> [<a href="https://arxiv.org/pdf/1909.03542">pdf</a>, <a href="https://arxiv.org/ps/1909.03542">ps</a>, <a href="https://arxiv.org/format/1909.03542">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Combinatorics">math.CO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Geometry">cs.CG</span> </div> </div> <p class="title is-5 mathjax"> When lattice cubes meet affine subspaces: a short note </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1909.03542v2-abstract-short" style="display: inline;"> We give short and simple proofs of what seem to be folklore results: * the maximum cardinality of the intersection of a lattice cube with an affine subspace; * the minimum number of affine subspaces needed to cover a lattice cube. </span> <span class="abstract-full has-text-grey-dark mathjax" id="1909.03542v2-abstract-full" style="display: none;"> We give short and simple proofs of what seem to be folklore results: * the maximum cardinality of the intersection of a lattice cube with an affine subspace; * the minimum number of affine subspaces needed to cover a lattice cube. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.03542v2-abstract-full').style.display = 'none'; document.getElementById('1909.03542v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 September, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 September, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">2 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1908.04921">arXiv:1908.04921</a> <span> [<a href="https://arxiv.org/pdf/1908.04921">pdf</a>, <a href="https://arxiv.org/ps/1908.04921">ps</a>, <a href="https://arxiv.org/format/1908.04921">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Complexity">cs.CC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Programming Languages">cs.PL</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.4204/EPTCS.298.2">10.4204/EPTCS.298.2 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> On the Elementary Affine Lambda-Calculus with and Without Fixed Points </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T+D">L锚 Th脿nh D农ng Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1908.04921v1-abstract-short" style="display: inline;"> The elementary affine lambda-calculus was introduced as a polyvalent setting for implicit computational complexity, allowing for characterizations of polynomial time and hyperexponential time predicates. But these results rely on type fixpoints (a.k.a. recursive types), and it was unknown whether this feature of the type system was really necessary. We give a positive answer by showing that witho… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1908.04921v1-abstract-full').style.display = 'inline'; document.getElementById('1908.04921v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1908.04921v1-abstract-full" style="display: none;"> The elementary affine lambda-calculus was introduced as a polyvalent setting for implicit computational complexity, allowing for characterizations of polynomial time and hyperexponential time predicates. But these results rely on type fixpoints (a.k.a. recursive types), and it was unknown whether this feature of the type system was really necessary. We give a positive answer by showing that without type fixpoints, we get a characterization of regular languages instead of polynomial time. The proof uses the semantic evaluation method. We also propose an aesthetic improvement on the characterization of the function classes FP and k-FEXPTIME in the presence of recursive types. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1908.04921v1-abstract-full').style.display = 'none'; document.getElementById('1908.04921v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 August, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">In Proceedings DICE-FOPARA 2019, arXiv:1908.04478</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> EPTCS 298, 2019, pp. 15-29 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1907.11705">arXiv:1907.11705</a> <span> [<a href="https://arxiv.org/pdf/1907.11705">pdf</a>, <a href="https://arxiv.org/ps/1907.11705">ps</a>, <a href="https://arxiv.org/format/1907.11705">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Data Structures and Algorithms">cs.DS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Low-Rank Matrix Completion: A Contemporary Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T">Luong Trung Nguyen</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J">Junhan Kim</a>, <a href="/search/cs?searchtype=author&query=Shim%2C+B">Byonghyo Shim</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1907.11705v1-abstract-short" style="display: inline;"> As a paradigm to recover unknown entries of a matrix from partial observations, low-rank matrix completion (LRMC) has generated a great deal of interest. Over the years, there have been lots of works on this topic but it might not be easy to grasp the essential knowledge from these studies. This is mainly because many of these works are highly theoretical or a proposal of new LRMC technique. In th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.11705v1-abstract-full').style.display = 'inline'; document.getElementById('1907.11705v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1907.11705v1-abstract-full" style="display: none;"> As a paradigm to recover unknown entries of a matrix from partial observations, low-rank matrix completion (LRMC) has generated a great deal of interest. Over the years, there have been lots of works on this topic but it might not be easy to grasp the essential knowledge from these studies. This is mainly because many of these works are highly theoretical or a proposal of new LRMC technique. In this paper, we give a contemporary survey on LRMC. In order to provide better view, insight, and understanding of potentials and limitations of LRMC, we present early scattered results in a structured and accessible way. Specifically, we classify the state-of-the-art LRMC techniques into two main categories and then explain each category in detail. We next discuss issues to be considered when one considers using LRMC techniques. These include intrinsic properties required for the matrix recovery and how to exploit a special structure in LRMC design. We also discuss the convolutional neural network (CNN) based LRMC algorithms exploiting the graph structure of a low-rank matrix. Further, we present the recovery performance and the computational complexity of the state-of-the-art LRMC techniques. Our hope is that this survey article will serve as a useful guide for practitioners and non-experts to catch the gist of LRMC. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.11705v1-abstract-full').style.display = 'none'; document.getElementById('1907.11705v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 July, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1907.00467">arXiv:1907.00467</a> <span> [<a href="https://arxiv.org/pdf/1907.00467">pdf</a>, <a href="https://arxiv.org/format/1907.00467">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Formal Languages and Automata Theory">cs.FL</span> </div> </div> <p class="title is-5 mathjax"> Typed lambda-calculi and superclasses of regular functions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1907.00467v1-abstract-short" style="display: inline;"> We propose to use Church encodings in typed lambda-calculi as the basis for an automata-theoretic counterpart of implicit computational complexity, in the same way that monadic second-order logic provides a counterpart to descriptive complexity. Specifically, we look at transductions i.e. string-to-string (or tree-to-tree) functions - in particular those with superlinear growth, such as polyregula… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.00467v1-abstract-full').style.display = 'inline'; document.getElementById('1907.00467v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1907.00467v1-abstract-full" style="display: none;"> We propose to use Church encodings in typed lambda-calculi as the basis for an automata-theoretic counterpart of implicit computational complexity, in the same way that monadic second-order logic provides a counterpart to descriptive complexity. Specifically, we look at transductions i.e. string-to-string (or tree-to-tree) functions - in particular those with superlinear growth, such as polyregular functions, HDT0L transductions and S茅nizergues's "k-computable mappings". Our first results towards this aim consist showing the inclusion of some transduction classes in some classes defined by lambda-calculi. In particular, this sheds light on a basic open question on the expressivity of the simply typed lambda-calculus. We also encode regular functions (and, by changing the type of programs considered, we get a larger subclass of polyregular functions) in the elementary affine lambda-calculus, a variant of linear logic originally designed for implicit computational complexity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.00467v1-abstract-full').style.display = 'none'; document.getElementById('1907.00467v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 June, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">23 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1906.02005">arXiv:1906.02005</a> <span> [<a href="https://arxiv.org/pdf/1906.02005">pdf</a>, <a href="https://arxiv.org/format/1906.02005">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</span> </div> </div> <p class="title is-5 mathjax"> A surrogate model for computational homogenization of elastostatics at finite strain using the HDMR-based neural network approximator </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen-Thanh%2C+V+M">Vien Minh Nguyen-Thanh</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T+K">Lu Trong Khiem Nguyen</a>, <a href="/search/cs?searchtype=author&query=Rabczuk%2C+T">Timon Rabczuk</a>, <a href="/search/cs?searchtype=author&query=Zhuang%2C+X">Xiaoying Zhuang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1906.02005v1-abstract-short" style="display: inline;"> We propose a surrogate model for two-scale computational homogenization of elastostatics at finite strains. The macroscopic constitutive law is made numerically available via an explicit formulation of the associated macro-energy density. This energy density is constructed by using a neural network architecture that mimics a high-dimensional model representation. The database for training this net… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.02005v1-abstract-full').style.display = 'inline'; document.getElementById('1906.02005v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1906.02005v1-abstract-full" style="display: none;"> We propose a surrogate model for two-scale computational homogenization of elastostatics at finite strains. The macroscopic constitutive law is made numerically available via an explicit formulation of the associated macro-energy density. This energy density is constructed by using a neural network architecture that mimics a high-dimensional model representation. The database for training this network is assembled through solving a set of microscopic boundary values problems with the prescribed macroscopic deformation gradients (input data) and subsequently retrieving the corresponding averaged energies (output data). Therefore, the two-scale computational procedure for the nonlinear elasticity can be broken down into two solvers for microscopic and macroscopic equilibrium equations that work separately in two stages, called the offline and online stages. A standard finite element method is employed to solve the equilibrium equation at the macroscale. As for mircoscopic problems, an FFT-based collocation method is applied in tandem with the Newton-Raphson iteration and the conjugate-gradient method. Particularly, we solve the microscopic equilibrium equation in the Lippmann-Schwinger form without resorting to the reference medium and thus avoid the fixed-point iteration that might require quite strict numerical stability condition in the nonlinear regime. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.02005v1-abstract-full').style.display = 'none'; document.getElementById('1906.02005v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 June, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1904.06849">arXiv:1904.06849</a> <span> [<a href="https://arxiv.org/pdf/1904.06849">pdf</a>, <a href="https://arxiv.org/ps/1904.06849">ps</a>, <a href="https://arxiv.org/format/1904.06849">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.4204/EPTCS.292.6">10.4204/EPTCS.292.6 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Coherent Interaction Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+T+D">L锚 Th脿nh D农ng Nguyen</a>, <a href="/search/cs?searchtype=author&query=Seiller%2C+T">Thomas Seiller</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1904.06849v1-abstract-short" style="display: inline;"> We introduce the notion of coherent graphs, and show how those can be used to define dynamic semantics for Multiplicative Linear Logic (MLL) extended with non-determinism. Thanks to the use of a coherence relation rather than mere formal sums of non-deterministic possibilities, our model enjoys some finiteness and sparsity properties. We also show how studying the semantic types generated by a s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.06849v1-abstract-full').style.display = 'inline'; document.getElementById('1904.06849v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1904.06849v1-abstract-full" style="display: none;"> We introduce the notion of coherent graphs, and show how those can be used to define dynamic semantics for Multiplicative Linear Logic (MLL) extended with non-determinism. Thanks to the use of a coherence relation rather than mere formal sums of non-deterministic possibilities, our model enjoys some finiteness and sparsity properties. We also show how studying the semantic types generated by a single "test" within our model of MLL naturally gives rise to a notion of proof net, which turns out to be exactly Retor茅's R&B-cographs. This revisits the old idea that multplicative proof net correctness is interactive, with a twist: types are characterized not by a set of counter-proofs but by a single non-deterministic counter-proof. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.06849v1-abstract-full').style.display = 'none'; document.getElementById('1904.06849v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 April, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">In Proceedings Linearity-TLLA 2018, arXiv:1904.06159</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> F.4.1 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> EPTCS 292, 2019, pp. 104-117 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1902.00196">arXiv:1902.00196</a> <span> [<a href="https://arxiv.org/pdf/1902.00196">pdf</a>, <a href="https://arxiv.org/format/1902.00196">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Complexity">cs.CC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Logic">math.LO</span> </div> </div> <p class="title is-5 mathjax"> Around finite second-order coherence spaces </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1902.00196v3-abstract-short" style="display: inline;"> Many applications of denotational semantics, such as higher-order model checking or the complexity of normalization, rely on finite semantics for monomorphic type systems. We exhibit such a finite semantics for a polymorphic purely linear language: more precisely, we show that in Girard's semantics of second-order linear logic using coherence spaces and normal functors, the denotations of multipli… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.00196v3-abstract-full').style.display = 'inline'; document.getElementById('1902.00196v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1902.00196v3-abstract-full" style="display: none;"> Many applications of denotational semantics, such as higher-order model checking or the complexity of normalization, rely on finite semantics for monomorphic type systems. We exhibit such a finite semantics for a polymorphic purely linear language: more precisely, we show that in Girard's semantics of second-order linear logic using coherence spaces and normal functors, the denotations of multiplicative-additive formulas are finite. This model is also effective, in the sense that the denotations of formulas and proofs are computable, as we show. We also establish analogous results for a second-order extension of Ehrhard's hypercoherences; while finiteness holds for the same reason as in coherence spaces, effectivity presents additional difficulties. Finally, we discuss the applications our our work to implicit computational complexity in linear (or affine) logic. In view of these applications, we study cardinality and complexity bounds in our finite semantics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.00196v3-abstract-full').style.display = 'none'; document.getElementById('1902.00196v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 May, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 February, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The v1 of this is being split into multiple smaller papers. A forthcoming paper with Pistone, Seiller and Tortora de Falco will cover the syntactic aspects not included in the present v3. Changes from v2: add hypercoherences</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 03B70; 68Q55; 18C50; 03F52; 03B47; 03B15; </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1901.10247">arXiv:1901.10247</a> <span> [<a href="https://arxiv.org/pdf/1901.10247">pdf</a>, <a href="https://arxiv.org/format/1901.10247">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.23638/LMCS-16(1:27)2020">10.23638/LMCS-16(1:27)2020 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Unique perfect matchings, forbidden transitions and proof nets for linear logic with Mix </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1901.10247v5-abstract-short" style="display: inline;"> This paper establishes a bridge between linear logic and mainstream graph theory, building on previous work by Retor茅 (2003). We show that the problem of correctness for MLL+Mix proof nets is equivalent to the problem of uniqueness of a perfect matching. By applying matching theory, we obtain new results for MLL+Mix proof nets: a linear-time correctness criterion, a quasi-linear sequentialization… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.10247v5-abstract-full').style.display = 'inline'; document.getElementById('1901.10247v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1901.10247v5-abstract-full" style="display: none;"> This paper establishes a bridge between linear logic and mainstream graph theory, building on previous work by Retor茅 (2003). We show that the problem of correctness for MLL+Mix proof nets is equivalent to the problem of uniqueness of a perfect matching. By applying matching theory, we obtain new results for MLL+Mix proof nets: a linear-time correctness criterion, a quasi-linear sequentialization algorithm, and a characterization of the sub-polynomial complexity of the correctness problem. We also use graph algorithms to compute the dependency relation of Bagnol et al. (2015) and the kingdom ordering of Bellin (1997), and relate them to the notion of blossom which is central to combinatorial maximum matching algorithms. In this journal version, we have added an explanation of Retor茅's "RB-graphs" in terms of a general construction on graphs with forbidden transitions. In fact, it is by analyzing RB-graphs that we arrived at this construction, and thus obtained a polynomial-time algorithm for finding trails avoiding forbidden transitions; the latter is among the material covered in another paper by the author focusing on graph theory (arXiv:1901.07028). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.10247v5-abstract-full').style.display = 'none'; document.getElementById('1901.10247v5-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 January, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 03F52; 68R10 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> F.4.1; G.2.2 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Logical Methods in Computer Science, Volume 16, Issue 1 (February 28, 2020) lmcs:5134 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1901.07028">arXiv:1901.07028</a> <span> [<a href="https://arxiv.org/pdf/1901.07028">pdf</a>, <a href="https://arxiv.org/ps/1901.07028">ps</a>, <a href="https://arxiv.org/format/1901.07028">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Discrete Mathematics">cs.DM</span> </div> </div> <p class="title is-5 mathjax"> Constrained path-finding and structure from acyclicity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguy%C3%AAn%2C+L+T+D">L锚 Th脿nh D农ng Nguy锚n</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1901.07028v2-abstract-short" style="display: inline;"> This note presents several results in graph theory inspired by the author's work in the proof theory of linear logic; these results are purely combinatorial and do not involve logic. We show that trails avoiding forbidden transitions, properly arc-colored directed trails and rainbow paths for complete multipartite color classes can be found in linear time, whereas finding rainbow paths is NP-com… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.07028v2-abstract-full').style.display = 'inline'; document.getElementById('1901.07028v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1901.07028v2-abstract-full" style="display: none;"> This note presents several results in graph theory inspired by the author's work in the proof theory of linear logic; these results are purely combinatorial and do not involve logic. We show that trails avoiding forbidden transitions, properly arc-colored directed trails and rainbow paths for complete multipartite color classes can be found in linear time, whereas finding rainbow paths is NP-complete for any other restriction on color classes. For the tractable cases, we also state new structural properties equivalent to Kotzig's theorem on the existence of bridges in unique perfect matchings. Another result on graphs equipped with unique perfect matchings that we prove here is the combinatorial counterpart of a theorem due to Bellin in linear logic: a connection between blossoms and bridge deletion orders. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.07028v2-abstract-full').style.display = 'none'; document.getElementById('1901.07028v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 January, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 January, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Unpublished notes, intended to serve as reference for the results announced in "On some tractable constraints on paths in graphs and in proofs" (CTW'18 workshop) and used in arXiv:1901.10247 / arXiv:1912.10606. May be turned into a proper publication in the not-so-distant future</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> F.2.2; G.2.2 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> F.2.2; G.2.2 </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Nguyen%2C+L+T&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Nguyen%2C+L+T&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Nguyen%2C+L+T&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository