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 93 results for author: <span class="mathjax">Gipp, B</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=Gipp%2C+B">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="Gipp, B"> </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=Gipp%2C+B&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="Gipp, B"> <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=Gipp%2C+B&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Gipp%2C+B&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Gipp%2C+B&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/2502.11926">arXiv:2502.11926</a> <span> [<a href="https://arxiv.org/pdf/2502.11926">pdf</a>, <a href="https://arxiv.org/format/2502.11926">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"> BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Muhammad%2C+S+H">Shamsuddeen Hassan Muhammad</a>, <a href="/search/cs?searchtype=author&query=Ousidhoum%2C+N">Nedjma Ousidhoum</a>, <a href="/search/cs?searchtype=author&query=Abdulmumin%2C+I">Idris Abdulmumin</a>, <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Beloucif%2C+M">Meriem Beloucif</a>, <a href="/search/cs?searchtype=author&query=de+Kock%2C+C">Christine de Kock</a>, <a href="/search/cs?searchtype=author&query=Surange%2C+N">Nirmal Surange</a>, <a href="/search/cs?searchtype=author&query=Teodorescu%2C+D">Daniela Teodorescu</a>, <a href="/search/cs?searchtype=author&query=Ahmad%2C+I+S">Ibrahim Said Ahmad</a>, <a href="/search/cs?searchtype=author&query=Adelani%2C+D+I">David Ifeoluwa Adelani</a>, <a href="/search/cs?searchtype=author&query=Aji%2C+A+F">Alham Fikri Aji</a>, <a href="/search/cs?searchtype=author&query=Ali%2C+F+D+M+A">Felermino D. M. A. Ali</a>, <a href="/search/cs?searchtype=author&query=Alimova%2C+I">Ilseyar Alimova</a>, <a href="/search/cs?searchtype=author&query=Araujo%2C+V">Vladimir Araujo</a>, <a href="/search/cs?searchtype=author&query=Babakov%2C+N">Nikolay Babakov</a>, <a href="/search/cs?searchtype=author&query=Baes%2C+N">Naomi Baes</a>, <a href="/search/cs?searchtype=author&query=Bucur%2C+A">Ana-Maria Bucur</a>, <a href="/search/cs?searchtype=author&query=Bukula%2C+A">Andiswa Bukula</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+G">Guanqun Cao</a>, <a href="/search/cs?searchtype=author&query=Cardenas%2C+R+T">Rodrigo Tufino Cardenas</a>, <a href="/search/cs?searchtype=author&query=Chevi%2C+R">Rendi Chevi</a>, <a href="/search/cs?searchtype=author&query=Chukwuneke%2C+C+I">Chiamaka Ijeoma Chukwuneke</a>, <a href="/search/cs?searchtype=author&query=Ciobotaru%2C+A">Alexandra Ciobotaru</a>, <a href="/search/cs?searchtype=author&query=Dementieva%2C+D">Daryna Dementieva</a> , et al. (23 additional authors not shown) </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="2502.11926v1-abstract-short" style="display: inline;"> People worldwide use language in subtle and complex ways to express emotions. While emotion recognition -- an umbrella term for several NLP tasks -- significantly impacts different applications in NLP and other fields, most work in the area is focused on high-resource languages. Therefore, this has led to major disparities in research and proposed solutions, especially for low-resource languages t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11926v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11926v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11926v1-abstract-full" style="display: none;"> People worldwide use language in subtle and complex ways to express emotions. While emotion recognition -- an umbrella term for several NLP tasks -- significantly impacts different applications in NLP and other fields, most work in the area is focused on high-resource languages. Therefore, this has led to major disparities in research and proposed solutions, especially for low-resource languages that suffer from the lack of high-quality datasets. In this paper, we present BRIGHTER-- a collection of multilabeled emotion-annotated datasets in 28 different languages. BRIGHTER covers predominantly low-resource languages from Africa, Asia, Eastern Europe, and Latin America, with instances from various domains annotated by fluent speakers. We describe the data collection and annotation processes and the challenges of building these datasets. Then, we report different experimental results for monolingual and crosslingual multi-label emotion identification, as well as intensity-level emotion recognition. We investigate results with and without using LLMs and analyse the large variability in performance across languages and text domains. We show that BRIGHTER datasets are a step towards bridging the gap in text-based emotion recognition and discuss their impact and utility. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11926v1-abstract-full').style.display = 'none'; document.getElementById('2502.11926v1-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> 17 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </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, under review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.10008">arXiv:2412.10008</a> <span> [<a href="https://arxiv.org/pdf/2412.10008">pdf</a>, <a href="https://arxiv.org/format/2412.10008">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"> Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhukova%2C+A">Anastasia Zhukova</a>, <a href="/search/cs?searchtype=author&query=Matt%2C+C+E">Christian E. Matt</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2412.10008v1-abstract-short" style="display: inline;"> Domain-specific languages that use a lot of specific terminology often fall into the category of low-resource languages. Collecting test datasets in a narrow domain is time-consuming and requires skilled human resources with domain knowledge and training for the annotation task. This study addresses the challenge of automated collecting test datasets to evaluate semantic search in low-resource dom… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.10008v1-abstract-full').style.display = 'inline'; document.getElementById('2412.10008v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.10008v1-abstract-full" style="display: none;"> Domain-specific languages that use a lot of specific terminology often fall into the category of low-resource languages. Collecting test datasets in a narrow domain is time-consuming and requires skilled human resources with domain knowledge and training for the annotation task. This study addresses the challenge of automated collecting test datasets to evaluate semantic search in low-resource domain-specific German language of the process industry. Our approach proposes an end-to-end annotation pipeline for automated query generation to the score reassessment of query-document pairs. To overcome the lack of text encoders trained in the German chemistry domain, we explore a principle of an ensemble of "weak" text encoders trained on common knowledge datasets. We combine individual relevance scores from diverse models to retrieve document candidates and relevance scores generated by an LLM, aiming to achieve consensus on query-document alignment. Evaluation results demonstrate that the ensemble method significantly improves alignment with human-assigned relevance scores, outperforming individual models in both inter-coder agreement and accuracy metrics. These findings suggest that ensemble learning can effectively adapt semantic search systems for specialized, low-resource languages, offering a practical solution to resource limitations in domain-specific contexts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.10008v1-abstract-full').style.display = 'none'; document.getElementById('2412.10008v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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 in the First Workshop on Language Models for Low-Resource Languages (LoResLM) co-located with the 31st International Conference on Computational Linguistics (COLING 2025)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.18444">arXiv:2411.18444</a> <span> [<a href="https://arxiv.org/pdf/2411.18444">pdf</a>, <a href="https://arxiv.org/format/2411.18444">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> <p class="title is-5 mathjax"> Is my Meeting Summary Good? Estimating Quality with a Multi-LLM Evaluator </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kirstein%2C+F">Frederic Kirstein</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2411.18444v1-abstract-short" style="display: inline;"> The quality of meeting summaries generated by natural language generation (NLG) systems is hard to measure automatically. Established metrics such as ROUGE and BERTScore have a relatively low correlation with human judgments and fail to capture nuanced errors. Recent studies suggest using large language models (LLMs), which have the benefit of better context understanding and adaption of error def… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.18444v1-abstract-full').style.display = 'inline'; document.getElementById('2411.18444v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.18444v1-abstract-full" style="display: none;"> The quality of meeting summaries generated by natural language generation (NLG) systems is hard to measure automatically. Established metrics such as ROUGE and BERTScore have a relatively low correlation with human judgments and fail to capture nuanced errors. Recent studies suggest using large language models (LLMs), which have the benefit of better context understanding and adaption of error definitions without training on a large number of human preference judgments. However, current LLM-based evaluators risk masking errors and can only serve as a weak proxy, leaving human evaluation the gold standard despite being costly and hard to compare across studies. In this work, we present MESA, an LLM-based framework employing a three-step assessment of individual error types, multi-agent discussion for decision refinement, and feedback-based self-training to refine error definition understanding and alignment with human judgment. We show that MESA's components enable thorough error detection, consistent rating, and adaptability to custom error guidelines. Using GPT-4o as its backbone, MESA achieves mid to high Point-Biserial correlation with human judgment in error detection and mid Spearman and Kendall correlation in reflecting error impact on summary quality, on average 0.25 higher than previous methods. The framework's flexibility in adapting to custom error guidelines makes it suitable for various tasks with limited human-labeled data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.18444v1-abstract-full').style.display = 'none'; document.getElementById('2411.18444v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11081">arXiv:2411.11081</a> <span> [<a href="https://arxiv.org/pdf/2411.11081">pdf</a>, <a href="https://arxiv.org/format/2411.11081">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"> The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Horych%2C+T">Tomas Horych</a>, <a href="/search/cs?searchtype=author&query=Mandl%2C+C">Christoph Mandl</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Greiner-Petter%2C+A">Andre Greiner-Petter</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Aizawa%2C+A">Akiko Aizawa</a>, <a href="/search/cs?searchtype=author&query=Spinde%2C+T">Timo Spinde</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="2411.11081v2-abstract-short" style="display: inline;"> High annotation costs from hiring or crowdsourcing complicate the creation of large, high-quality datasets needed for training reliable text classifiers. Recent research suggests using Large Language Models (LLMs) to automate the annotation process, reducing these costs while maintaining data quality. LLMs have shown promising results in annotating downstream tasks like hate speech detection and p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11081v2-abstract-full').style.display = 'inline'; document.getElementById('2411.11081v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11081v2-abstract-full" style="display: none;"> High annotation costs from hiring or crowdsourcing complicate the creation of large, high-quality datasets needed for training reliable text classifiers. Recent research suggests using Large Language Models (LLMs) to automate the annotation process, reducing these costs while maintaining data quality. LLMs have shown promising results in annotating downstream tasks like hate speech detection and political framing. Building on the success in these areas, this study investigates whether LLMs are viable for annotating the complex task of media bias detection and whether a downstream media bias classifier can be trained on such data. We create annolexical, the first large-scale dataset for media bias classification with over 48000 synthetically annotated examples. Our classifier, fine-tuned on this dataset, surpasses all of the annotator LLMs by 5-9 percent in Matthews Correlation Coefficient (MCC) and performs close to or outperforms the model trained on human-labeled data when evaluated on two media bias benchmark datasets (BABE and BASIL). This study demonstrates how our approach significantly reduces the cost of dataset creation in the media bias domain and, by extension, the development of classifiers, while our subsequent behavioral stress-testing reveals some of its current limitations and trade-offs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11081v2-abstract-full').style.display = 'none'; document.getElementById('2411.11081v2-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> 24 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.14545">arXiv:2410.14545</a> <span> [<a href="https://arxiv.org/pdf/2410.14545">pdf</a>, <a href="https://arxiv.org/format/2410.14545">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> <p class="title is-5 mathjax"> Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kirstein%2C+F">Frederic Kirstein</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Kratel%2C+R">Robert Kratel</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2410.14545v1-abstract-short" style="display: inline;"> Meeting summarization is crucial in digital communication, but existing solutions struggle with salience identification to generate personalized, workable summaries, and context understanding to fully comprehend the meetings' content. Previous attempts to address these issues by considering related supplementary resources (e.g., presentation slides) alongside transcripts are hindered by models' li… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14545v1-abstract-full').style.display = 'inline'; document.getElementById('2410.14545v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.14545v1-abstract-full" style="display: none;"> Meeting summarization is crucial in digital communication, but existing solutions struggle with salience identification to generate personalized, workable summaries, and context understanding to fully comprehend the meetings' content. Previous attempts to address these issues by considering related supplementary resources (e.g., presentation slides) alongside transcripts are hindered by models' limited context sizes and handling the additional complexities of the multi-source tasks, such as identifying relevant information in additional files and seamlessly aligning it with the meeting content. This work explores multi-source meeting summarization considering supplementary materials through a three-stage large language model approach: identifying transcript passages needing additional context, inferring relevant details from supplementary materials and inserting them into the transcript, and generating a summary from this enriched transcript. Our multi-source approach enhances model understanding, increasing summary relevance by ~9% and producing more content-rich outputs. We introduce a personalization protocol that extracts participant characteristics and tailors summaries accordingly, improving informativeness by ~10%. This work further provides insights on performance-cost trade-offs across four leading model families, including edge-device capable options. Our approach can be extended to similar complex generative tasks benefitting from additional resources and personalization, such as dialogue systems and action planning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14545v1-abstract-full').style.display = 'none'; document.getElementById('2410.14545v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.11919">arXiv:2407.11919</a> <span> [<a href="https://arxiv.org/pdf/2407.11919">pdf</a>, <a href="https://arxiv.org/format/2407.11919">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> <p class="title is-5 mathjax"> What's Wrong? Refining Meeting Summaries with LLM Feedback </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kirstein%2C+F">Frederic Kirstein</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2407.11919v1-abstract-short" style="display: inline;"> Meeting summarization has become a critical task since digital encounters have become a common practice. Large language models (LLMs) show great potential in summarization, offering enhanced coherence and context understanding compared to traditional methods. However, they still struggle to maintain relevance and avoid hallucination. We introduce a multi-LLM correction approach for meeting summari… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.11919v1-abstract-full').style.display = 'inline'; document.getElementById('2407.11919v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.11919v1-abstract-full" style="display: none;"> Meeting summarization has become a critical task since digital encounters have become a common practice. Large language models (LLMs) show great potential in summarization, offering enhanced coherence and context understanding compared to traditional methods. However, they still struggle to maintain relevance and avoid hallucination. We introduce a multi-LLM correction approach for meeting summarization using a two-phase process that mimics the human review process: mistake identification and summary refinement. We release QMSum Mistake, a dataset of 200 automatically generated meeting summaries annotated by humans on nine error types, including structural, omission, and irrelevance errors. Our experiments show that these errors can be identified with high accuracy by an LLM. We transform identified mistakes into actionable feedback to improve the quality of a given summary measured by relevance, informativeness, conciseness, and coherence. This post-hoc refinement effectively improves summary quality by leveraging multiple LLMs to validate output quality. Our multi-LLM approach for meeting summarization shows potential for similar complex text generation tasks requiring robustness, action planning, and discussion towards a goal. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.11919v1-abstract-full').style.display = 'none'; document.getElementById('2407.11919v1-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.03192">arXiv:2407.03192</a> <span> [<a href="https://arxiv.org/pdf/2407.03192">pdf</a>, <a href="https://arxiv.org/format/2407.03192">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</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"> CiteAssist: A System for Automated Preprint Citation and BibTeX Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kaesberg%2C+L+B">Lars Benedikt Kaesberg</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2407.03192v1-abstract-short" style="display: inline;"> We present CiteAssist, a system to automate the generation of BibTeX entries for preprints, streamlining the process of bibliographic annotation. Our system extracts metadata, such as author names, titles, publication dates, and keywords, to create standardized annotations within the document. CiteAssist automatically attaches the BibTeX citation to the end of a PDF and links it on the first page… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.03192v1-abstract-full').style.display = 'inline'; document.getElementById('2407.03192v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.03192v1-abstract-full" style="display: none;"> We present CiteAssist, a system to automate the generation of BibTeX entries for preprints, streamlining the process of bibliographic annotation. Our system extracts metadata, such as author names, titles, publication dates, and keywords, to create standardized annotations within the document. CiteAssist automatically attaches the BibTeX citation to the end of a PDF and links it on the first page of the document so other researchers gain immediate access to the correct citation of the article. This method promotes platform flexibility by ensuring that annotations remain accessible regardless of the repository used to publish or access the preprint. The annotations remain available even if the preprint is viewed externally to CiteAssist. Additionally, the system adds relevant related papers based on extracted keywords to the preprint, providing researchers with additional publications besides those in related work for further reading. Researchers can enhance their preprints organization and reference management workflows through a free and publicly available web interface. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.03192v1-abstract-full').style.display = 'none'; document.getElementById('2407.03192v1-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> 3 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">Published at SDProc @ ACL 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/2407.02302">arXiv:2407.02302</a> <span> [<a href="https://arxiv.org/pdf/2407.02302">pdf</a>, <a href="https://arxiv.org/format/2407.02302">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"> Towards Human Understanding of Paraphrase Types in ChatGPT </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Meier%2C+D">Dominik Meier</a>, <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2407.02302v1-abstract-short" style="display: inline;"> Paraphrases represent a human's intuitive ability to understand expressions presented in various different ways. Current paraphrase evaluations of language models primarily use binary approaches, offering limited interpretability of specific text changes. Atomic paraphrase types (APT) decompose paraphrases into different linguistic changes and offer a granular view of the flexibility in linguistic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.02302v1-abstract-full').style.display = 'inline'; document.getElementById('2407.02302v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.02302v1-abstract-full" style="display: none;"> Paraphrases represent a human's intuitive ability to understand expressions presented in various different ways. Current paraphrase evaluations of language models primarily use binary approaches, offering limited interpretability of specific text changes. Atomic paraphrase types (APT) decompose paraphrases into different linguistic changes and offer a granular view of the flexibility in linguistic expression (e.g., a shift in syntax or vocabulary used). In this study, we assess the human preferences towards ChatGPT in generating English paraphrases with ten APTs and five prompting techniques. We introduce APTY (Atomic Paraphrase TYpes), a dataset of 500 sentence-level and word-level annotations by 15 annotators. The dataset also provides a human preference ranking of paraphrases with different types that can be used to fine-tune models with RLHF and DPO methods. Our results reveal that ChatGPT can generate simple APTs, such as additions and deletions, but struggle with complex structures (e.g., subordination changes). This study contributes to understanding which aspects of paraphrasing language models have already succeeded at understanding and what remains elusive. In addition, our curated datasets can be used to develop language models with specific linguistic capabilities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.02302v1-abstract-full').style.display = 'none'; document.getElementById('2407.02302v1-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.19898">arXiv:2406.19898</a> <span> [<a href="https://arxiv.org/pdf/2406.19898">pdf</a>, <a href="https://arxiv.org/format/2406.19898">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"> Paraphrase Types Elicit Prompt Engineering Capabilities </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yang Xu</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2406.19898v4-abstract-short" style="display: inline;"> Much of the success of modern language models depends on finding a suitable prompt to instruct the model. Until now, it has been largely unknown how variations in the linguistic expression of prompts affect these models. This study systematically and empirically evaluates which linguistic features influence models through paraphrase types, i.e., different linguistic changes at particular positions… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19898v4-abstract-full').style.display = 'inline'; document.getElementById('2406.19898v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.19898v4-abstract-full" style="display: none;"> Much of the success of modern language models depends on finding a suitable prompt to instruct the model. Until now, it has been largely unknown how variations in the linguistic expression of prompts affect these models. This study systematically and empirically evaluates which linguistic features influence models through paraphrase types, i.e., different linguistic changes at particular positions. We measure behavioral changes for five models across 120 tasks and six families of paraphrases (i.e., morphology, syntax, lexicon, lexico-syntax, discourse, and others). We also control for other prompt engineering factors (e.g., prompt length, lexical diversity, and proximity to training data). Our results show a potential for language models to improve tasks when their prompts are adapted in specific paraphrase types (e.g., 6.7% median gain in Mixtral 8x7B; 5.5% in LLaMA 3 8B). In particular, changes in morphology and lexicon, i.e., the vocabulary used, showed promise in improving prompts. These findings contribute to developing more robust language models capable of handling variability in linguistic expression. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19898v4-abstract-full').style.display = 'none'; document.getElementById('2406.19898v4-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 June, 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">Journal ref:</span> EMNLP 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.07494">arXiv:2406.07494</a> <span> [<a href="https://arxiv.org/pdf/2406.07494">pdf</a>, <a href="https://arxiv.org/format/2406.07494">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> <p class="title is-5 mathjax"> CADS: A Systematic Literature Review on the Challenges of Abstractive Dialogue Summarization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kirstein%2C+F">Frederic Kirstein</a>, <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</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="2406.07494v2-abstract-short" style="display: inline;"> Abstractive dialogue summarization is the task of distilling conversations into informative and concise summaries. Although reviews have been conducted on this topic, there is a lack of comprehensive work detailing the challenges of dialogue summarization, unifying the differing understanding of the task, and aligning proposed techniques, datasets, and evaluation metrics with the challenges. This… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.07494v2-abstract-full').style.display = 'inline'; document.getElementById('2406.07494v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.07494v2-abstract-full" style="display: none;"> Abstractive dialogue summarization is the task of distilling conversations into informative and concise summaries. Although reviews have been conducted on this topic, there is a lack of comprehensive work detailing the challenges of dialogue summarization, unifying the differing understanding of the task, and aligning proposed techniques, datasets, and evaluation metrics with the challenges. This article summarizes the research on Transformer-based abstractive summarization for English dialogues by systematically reviewing 1262 unique research papers published between 2019 and 2024, relying on the Semantic Scholar and DBLP databases. We cover the main challenges present in dialog summarization (i.e., language, structure, comprehension, speaker, salience, and factuality) and link them to corresponding techniques such as graph-based approaches, additional training tasks, and planning strategies, which typically overly rely on BART-based encoder-decoder models. We find that while some challenges, like language, have seen considerable progress, mainly due to training methods, others, such as comprehension, factuality, and salience, remain difficult and hold significant research opportunities. We investigate how these approaches are typically assessed, covering the datasets for the subdomains of dialogue (e.g., meeting, medical), the established automatic metrics and human evaluation approaches for assessing scores and annotator agreement. We observe that only a few datasets span across all subdomains. The ROUGE metric is the most used, while human evaluation is frequently reported without sufficient detail on inner-annotator agreement and annotation guidelines. Additionally, we discuss the possible implications of the recently explored large language models and conclude that despite a potential shift in relevance and difficulty, our described challenge taxonomy remains relevant. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.07494v2-abstract-full').style.display = 'none'; document.getElementById('2406.07494v2-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.15604">arXiv:2405.15604</a> <span> [<a href="https://arxiv.org/pdf/2405.15604">pdf</a>, <a href="https://arxiv.org/format/2405.15604">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"> Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Becker%2C+J">Jonas Becker</a>, <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</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="2405.15604v3-abstract-short" style="display: inline;"> Text generation has become more accessible than ever, and the increasing interest in these systems, especially those using large language models, has spurred an increasing number of related publications. We provide a systematic literature review comprising 244 selected papers between 2017 and 2024. This review categorizes works in text generation into five main tasks: open-ended text generation, s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15604v3-abstract-full').style.display = 'inline'; document.getElementById('2405.15604v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.15604v3-abstract-full" style="display: none;"> Text generation has become more accessible than ever, and the increasing interest in these systems, especially those using large language models, has spurred an increasing number of related publications. We provide a systematic literature review comprising 244 selected papers between 2017 and 2024. This review categorizes works in text generation into five main tasks: open-ended text generation, summarization, translation, paraphrasing, and question answering. For each task, we review their relevant characteristics, sub-tasks, and specific challenges (e.g., missing datasets for multi-document summarization, coherence in story generation, and complex reasoning for question answering). Additionally, we assess current approaches for evaluating text generation systems and ascertain problems with current metrics. Our investigation shows nine prominent challenges common to all tasks and sub-tasks in recent text generation publications: bias, reasoning, hallucinations, misuse, privacy, interpretability, transparency, datasets, and computing. We provide a detailed analysis of these challenges, their potential solutions, and which gaps still require further engagement from the community. This systematic literature review targets two main audiences: early career researchers in natural language processing looking for an overview of the field and promising research directions, as well as experienced researchers seeking a detailed view of tasks, evaluation methodologies, open challenges, and recent mitigation strategies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15604v3-abstract-full').style.display = 'none'; document.getElementById('2405.15604v3-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> 29 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 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">35 pages, 2 figures, 2 tables, Under review</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> A.1; I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.11124">arXiv:2404.11124</a> <span> [<a href="https://arxiv.org/pdf/2404.11124">pdf</a>, <a href="https://arxiv.org/format/2404.11124">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> <p class="title is-5 mathjax"> What's under the hood: Investigating Automatic Metrics on Meeting Summarization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kirstein%2C+F">Frederic Kirstein</a>, <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2404.11124v2-abstract-short" style="display: inline;"> Meeting summarization has become a critical task considering the increase in online interactions. While new techniques are introduced regularly, their evaluation uses metrics not designed to capture meeting-specific errors, undermining effective evaluation. This paper investigates what the frequently used automatic metrics capture and which errors they mask by correlating automatic metric scores w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.11124v2-abstract-full').style.display = 'inline'; document.getElementById('2404.11124v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.11124v2-abstract-full" style="display: none;"> Meeting summarization has become a critical task considering the increase in online interactions. While new techniques are introduced regularly, their evaluation uses metrics not designed to capture meeting-specific errors, undermining effective evaluation. This paper investigates what the frequently used automatic metrics capture and which errors they mask by correlating automatic metric scores with human evaluations across a broad error taxonomy. We commence with a comprehensive literature review on English meeting summarization to define key challenges like speaker dynamics and contextual turn-taking and error types such as missing information and linguistic inaccuracy, concepts previously loosely defined in the field. We examine the relationship between characteristic challenges and errors by using annotated transcripts and summaries from Transformer-based sequence-to-sequence and autoregressive models from the general summary QMSum dataset. Through experimental validation, we find that different model architectures respond variably to challenges in meeting transcripts, resulting in different pronounced links between challenges and errors. Current default-used metrics struggle to capture observable errors, showing weak to mid-correlations, while a third of the correlations show trends of error masking. Only a subset reacts accurately to specific errors, while most correlations show either unresponsiveness or failure to reflect the error's impact on summary quality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.11124v2-abstract-full').style.display = 'none'; document.getElementById('2404.11124v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 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/2404.00344">arXiv:2404.00344</a> <span> [<a href="https://arxiv.org/pdf/2404.00344">pdf</a>, <a href="https://arxiv.org/format/2404.00344">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Satpute%2C+A">Ankit Satpute</a>, <a href="/search/cs?searchtype=author&query=Giessing%2C+N">Noah Giessing</a>, <a href="/search/cs?searchtype=author&query=Greiner-Petter%2C+A">Andre Greiner-Petter</a>, <a href="/search/cs?searchtype=author&query=Schubotz%2C+M">Moritz Schubotz</a>, <a href="/search/cs?searchtype=author&query=Teschke%2C+O">Olaf Teschke</a>, <a href="/search/cs?searchtype=author&query=Aizawa%2C+A">Akiko Aizawa</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2404.00344v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have demonstrated exceptional capabilities in various natural language tasks, often achieving performances that surpass those of humans. Despite these advancements, the domain of mathematics presents a distinctive challenge, primarily due to its specialized structure and the precision it demands. In this study, we adopted a two-step approach for investigating the profi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.00344v1-abstract-full').style.display = 'inline'; document.getElementById('2404.00344v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.00344v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have demonstrated exceptional capabilities in various natural language tasks, often achieving performances that surpass those of humans. Despite these advancements, the domain of mathematics presents a distinctive challenge, primarily due to its specialized structure and the precision it demands. In this study, we adopted a two-step approach for investigating the proficiency of LLMs in answering mathematical questions. First, we employ the most effective LLMs, as identified by their performance on math question-answer benchmarks, to generate answers to 78 questions from the Math Stack Exchange (MSE). Second, a case analysis is conducted on the LLM that showed the highest performance, focusing on the quality and accuracy of its answers through manual evaluation. We found that GPT-4 performs best (nDCG of 0.48 and P@10 of 0.37) amongst existing LLMs fine-tuned for answering mathematics questions and outperforms the current best approach on ArqMATH3 Task1, considering P@10. Our Case analysis indicates that while the GPT-4 can generate relevant responses in certain instances, it does not consistently answer all questions accurately. This paper explores the current limitations of LLMs in navigating complex mathematical problem-solving. Through case analysis, we shed light on the gaps in LLM capabilities within mathematics, thereby setting the stage for future research and advancements in AI-driven mathematical reasoning. We make our code and findings publicly available for research: \url{https://github.com/gipplab/LLM-Investig-MathStackExchange} <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.00344v1-abstract-full').style.display = 'none'; document.getElementById('2404.00344v1-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 March, 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">Accepted for publication at the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) July 14--18, 2024, Washington D.C.,USA</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.07910">arXiv:2403.07910</a> <span> [<a href="https://arxiv.org/pdf/2403.07910">pdf</a>, <a href="https://arxiv.org/format/2403.07910">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</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"> MAGPIE: Multi-Task Media-Bias Analysis Generalization for Pre-Trained Identification of Expressions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Horych%2C+T">Tom谩拧 Horych</a>, <a href="/search/cs?searchtype=author&query=Wessel%2C+M">Martin Wessel</a>, <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Wa%C3%9Fmuth%2C+J">Jerome Wa脽muth</a>, <a href="/search/cs?searchtype=author&query=Greiner-Petter%2C+A">Andr茅 Greiner-Petter</a>, <a href="/search/cs?searchtype=author&query=Aizawa%2C+A">Akiko Aizawa</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Spinde%2C+T">Timo Spinde</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="2403.07910v2-abstract-short" style="display: inline;"> Media bias detection poses a complex, multifaceted problem traditionally tackled using single-task models and small in-domain datasets, consequently lacking generalizability. To address this, we introduce MAGPIE, the first large-scale multi-task pre-training approach explicitly tailored for media bias detection. To enable pre-training at scale, we present Large Bias Mixture (LBM), a compilation of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.07910v2-abstract-full').style.display = 'inline'; document.getElementById('2403.07910v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.07910v2-abstract-full" style="display: none;"> Media bias detection poses a complex, multifaceted problem traditionally tackled using single-task models and small in-domain datasets, consequently lacking generalizability. To address this, we introduce MAGPIE, the first large-scale multi-task pre-training approach explicitly tailored for media bias detection. To enable pre-training at scale, we present Large Bias Mixture (LBM), a compilation of 59 bias-related tasks. MAGPIE outperforms previous approaches in media bias detection on the Bias Annotation By Experts (BABE) dataset, with a relative improvement of 3.3% F1-score. MAGPIE also performs better than previous models on 5 out of 8 tasks in the Media Bias Identification Benchmark (MBIB). Using a RoBERTa encoder, MAGPIE needs only 15% of finetuning steps compared to single-task approaches. Our evaluation shows, for instance, that tasks like sentiment and emotionality boost all learning, all tasks enhance fake news detection, and scaling tasks leads to the best results. MAGPIE confirms that MTL is a promising approach for addressing media bias detection, enhancing the accuracy and efficiency of existing models. Furthermore, LBM is the first available resource collection focused on media bias MTL. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.07910v2-abstract-full').style.display = 'none'; document.getElementById('2403.07910v2-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 February, 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/2402.12046">arXiv:2402.12046</a> <span> [<a href="https://arxiv.org/pdf/2402.12046">pdf</a>, <a href="https://arxiv.org/format/2402.12046">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</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"> Citation Amnesia: On The Recency Bias of NLP and Other Academic Fields </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Abdalla%2C+M">Mohamed Abdalla</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Mohammad%2C+S+M">Saif M. Mohammad</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="2402.12046v2-abstract-short" style="display: inline;"> This study examines the tendency to cite older work across 20 fields of study over 43 years (1980--2023). We put NLP's propensity to cite older work in the context of these 20 other fields to analyze whether NLP shows similar temporal citation patterns to these other fields over time or whether differences can be observed. Our analysis, based on a dataset of approximately 240 million papers, revea… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.12046v2-abstract-full').style.display = 'inline'; document.getElementById('2402.12046v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.12046v2-abstract-full" style="display: none;"> This study examines the tendency to cite older work across 20 fields of study over 43 years (1980--2023). We put NLP's propensity to cite older work in the context of these 20 other fields to analyze whether NLP shows similar temporal citation patterns to these other fields over time or whether differences can be observed. Our analysis, based on a dataset of approximately 240 million papers, reveals a broader scientific trend: many fields have markedly declined in citing older works (e.g., psychology, computer science). We term this decline a 'citation age recession', analogous to how economists define periods of reduced economic activity. The trend is strongest in NLP and ML research (-12.8% and -5.5% in citation age from previous peaks). Our results suggest that citing more recent works is not directly driven by the growth in publication rates (-3.4% across fields; -5.2% in humanities; -5.5% in formal sciences) -- even when controlling for an increase in the volume of papers. Our findings raise questions about the scientific community's engagement with past literature, particularly for NLP, and the potential consequences of neglecting older but relevant research. The data and a demo showcasing our results are publicly available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.12046v2-abstract-full').style.display = 'none'; document.getElementById('2402.12046v2-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> COLING 2025 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.02996">arXiv:2402.02996</a> <span> [<a href="https://arxiv.org/pdf/2402.02996">pdf</a>, <a href="https://arxiv.org/format/2402.02996">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> <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"> Text-Guided Image Clustering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Stephan%2C+A">Andreas Stephan</a>, <a href="/search/cs?searchtype=author&query=Miklautz%2C+L">Lukas Miklautz</a>, <a href="/search/cs?searchtype=author&query=Sidak%2C+K">Kevin Sidak</a>, <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Plant%2C+C">Claudia Plant</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+B">Benjamin Roth</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="2402.02996v2-abstract-short" style="display: inline;"> Image clustering divides a collection of images into meaningful groups, typically interpreted post-hoc via human-given annotations. Those are usually in the form of text, begging the question of using text as an abstraction for image clustering. Current image clustering methods, however, neglect the use of generated textual descriptions. We, therefore, propose Text-Guided Image Clustering, i.e., g… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.02996v2-abstract-full').style.display = 'inline'; document.getElementById('2402.02996v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.02996v2-abstract-full" style="display: none;"> Image clustering divides a collection of images into meaningful groups, typically interpreted post-hoc via human-given annotations. Those are usually in the form of text, begging the question of using text as an abstraction for image clustering. Current image clustering methods, however, neglect the use of generated textual descriptions. We, therefore, propose Text-Guided Image Clustering, i.e., generating text using image captioning and visual question-answering (VQA) models and subsequently clustering the generated text. Further, we introduce a novel approach to inject task- or domain knowledge for clustering by prompting VQA models. Across eight diverse image clustering datasets, our results show that the obtained text representations often outperform image features. Additionally, we propose a counting-based cluster explainability method. Our evaluations show that the derived keyword-based explanations describe clusters better than the respective cluster accuracy suggests. Overall, this research challenges traditional approaches and paves the way for a paradigm shift in image clustering, using generated text. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.02996v2-abstract-full').style.display = 'none'; document.getElementById('2402.02996v2-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> 19 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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 EACL 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/2401.16969">arXiv:2401.16969</a> <span> [<a href="https://arxiv.org/pdf/2401.16969">pdf</a>, <a href="https://arxiv.org/ps/2401.16969">ps</a>, <a href="https://arxiv.org/format/2401.16969">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</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/10.1007/978-3-031-56066-8_2">10.1007/978-3-031-56066-8_2 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Taxonomy of Mathematical Plagiarism </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Satpute%2C+A">Ankit Satpute</a>, <a href="/search/cs?searchtype=author&query=Greiner-Petter%2C+A">Andre Greiner-Petter</a>, <a href="/search/cs?searchtype=author&query=Gie%C3%9Fing%2C+N">Noah Gie脽ing</a>, <a href="/search/cs?searchtype=author&query=Beckenbach%2C+I">Isabel Beckenbach</a>, <a href="/search/cs?searchtype=author&query=Schubotz%2C+M">Moritz Schubotz</a>, <a href="/search/cs?searchtype=author&query=Teschke%2C+O">Olaf Teschke</a>, <a href="/search/cs?searchtype=author&query=Aizawa%2C+A">Akiko Aizawa</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2401.16969v2-abstract-short" style="display: inline;"> Plagiarism is a pressing concern, even more so with the availability of large language models. Existing plagiarism detection systems reliably find copied and moderately reworded text but fail for idea plagiarism, especially in mathematical science, which heavily uses formal mathematical notation. We make two contributions. First, we establish a taxonomy of mathematical content reuse by annotating… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.16969v2-abstract-full').style.display = 'inline'; document.getElementById('2401.16969v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.16969v2-abstract-full" style="display: none;"> Plagiarism is a pressing concern, even more so with the availability of large language models. Existing plagiarism detection systems reliably find copied and moderately reworded text but fail for idea plagiarism, especially in mathematical science, which heavily uses formal mathematical notation. We make two contributions. First, we establish a taxonomy of mathematical content reuse by annotating potentially plagiarised 122 scientific document pairs. Second, we analyze the best-performing approaches to detect plagiarism and mathematical content similarity on the newly established taxonomy. We found that the best-performing methods for plagiarism and math content similarity achieve an overall detection score (PlagDet) of 0.06 and 0.16, respectively. The best-performing methods failed to detect most cases from all seven newly established math similarity types. Outlined contributions will benefit research in plagiarism detection systems, recommender systems, question-answering systems, and search engines. We make our experiment's code and annotated dataset available to the community: https://github.com/gipplab/Taxonomy-of-Mathematical-Plagiarism <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.16969v2-abstract-full').style.display = 'none'; document.getElementById('2401.16969v2-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">46th European Conference on Information Retrieval (ECIR)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.16148">arXiv:2312.16148</a> <span> [<a href="https://arxiv.org/pdf/2312.16148">pdf</a>, <a href="https://arxiv.org/format/2312.16148">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"> The Media Bias Taxonomy: A Systematic Literature Review on the Forms and Automated Detection of Media Bias </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Spinde%2C+T">Timo Spinde</a>, <a href="/search/cs?searchtype=author&query=Hinterreiter%2C+S">Smi Hinterreiter</a>, <a href="/search/cs?searchtype=author&query=Haak%2C+F">Fabian Haak</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Giese%2C+H">Helge Giese</a>, <a href="/search/cs?searchtype=author&query=Meuschke%2C+N">Norman Meuschke</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2312.16148v3-abstract-short" style="display: inline;"> The way the media presents events can significantly affect public perception, which in turn can alter people's beliefs and views. Media bias describes a one-sided or polarizing perspective on a topic. This article summarizes the research on computational methods to detect media bias by systematically reviewing 3140 research papers published between 2019 and 2022. To structure our review and suppor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.16148v3-abstract-full').style.display = 'inline'; document.getElementById('2312.16148v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.16148v3-abstract-full" style="display: none;"> The way the media presents events can significantly affect public perception, which in turn can alter people's beliefs and views. Media bias describes a one-sided or polarizing perspective on a topic. This article summarizes the research on computational methods to detect media bias by systematically reviewing 3140 research papers published between 2019 and 2022. To structure our review and support a mutual understanding of bias across research domains, we introduce the Media Bias Taxonomy, which provides a coherent overview of the current state of research on media bias from different perspectives. We show that media bias detection is a highly active research field, in which transformer-based classification approaches have led to significant improvements in recent years. These improvements include higher classification accuracy and the ability to detect more fine-granular types of bias. However, we have identified a lack of interdisciplinarity in existing projects, and a need for more awareness of the various types of media bias to support methodologically thorough performance evaluations of media bias detection systems. Concluding from our analysis, we see the integration of recent machine learning advancements with reliable and diverse bias assessment strategies from other research areas as the most promising area for future research contributions in the field. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.16148v3-abstract-full').style.display = 'none'; document.getElementById('2312.16148v3-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.14870">arXiv:2310.14870</a> <span> [<a href="https://arxiv.org/pdf/2310.14870">pdf</a>, <a href="https://arxiv.org/format/2310.14870">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="Digital Libraries">cs.DL</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/v1/2023.emnlp-main.797">10.18653/v1/2023.emnlp-main.797 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> We are Who We Cite: Bridges of Influence Between Natural Language Processing and Other Academic Fields </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Abdalla%2C+M">Mohamed Abdalla</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Mohammad%2C+S+M">Saif M. Mohammad</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="2310.14870v3-abstract-short" style="display: inline;"> Natural Language Processing (NLP) is poised to substantially influence the world. However, significant progress comes hand-in-hand with substantial risks. Addressing them requires broad engagement with various fields of study. Yet, little empirical work examines the state of such engagement (past or current). In this paper, we quantify the degree of influence between 23 fields of study and NLP (on… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.14870v3-abstract-full').style.display = 'inline'; document.getElementById('2310.14870v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.14870v3-abstract-full" style="display: none;"> Natural Language Processing (NLP) is poised to substantially influence the world. However, significant progress comes hand-in-hand with substantial risks. Addressing them requires broad engagement with various fields of study. Yet, little empirical work examines the state of such engagement (past or current). In this paper, we quantify the degree of influence between 23 fields of study and NLP (on each other). We analyzed ~77k NLP papers, ~3.1m citations from NLP papers to other papers, and ~1.8m citations from other papers to NLP papers. We show that, unlike most fields, the cross-field engagement of NLP, measured by our proposed Citation Field Diversity Index (CFDI), has declined from 0.58 in 1980 to 0.31 in 2022 (an all-time low). In addition, we find that NLP has grown more insular -- citing increasingly more NLP papers and having fewer papers that act as bridges between fields. NLP citations are dominated by computer science; Less than 8% of NLP citations are to linguistics, and less than 3% are to math and psychology. These findings underscore NLP's urgent need to reflect on its engagement with various fields. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.14870v3-abstract-full').style.display = 'none'; document.getElementById('2310.14870v3-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 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">Published at EMNLP 2023</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> EMNLP 2023 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.14863">arXiv:2310.14863</a> <span> [<a href="https://arxiv.org/pdf/2310.14863">pdf</a>, <a href="https://arxiv.org/format/2310.14863">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/10.18653/v1/2023.emnlp-main.746">10.18653/v1/2023.emnlp-main.746 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Paraphrase Types for Generation and Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</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="2310.14863v3-abstract-short" style="display: inline;"> Current approaches in paraphrase generation and detection heavily rely on a single general similarity score, ignoring the intricate linguistic properties of language. This paper introduces two new tasks to address this shortcoming by considering paraphrase types - specific linguistic perturbations at particular text positions. We name these tasks Paraphrase Type Generation and Paraphrase Type Dete… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.14863v3-abstract-full').style.display = 'inline'; document.getElementById('2310.14863v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.14863v3-abstract-full" style="display: none;"> Current approaches in paraphrase generation and detection heavily rely on a single general similarity score, ignoring the intricate linguistic properties of language. This paper introduces two new tasks to address this shortcoming by considering paraphrase types - specific linguistic perturbations at particular text positions. We name these tasks Paraphrase Type Generation and Paraphrase Type Detection. Our results suggest that while current techniques perform well in a binary classification scenario, i.e., paraphrased or not, the inclusion of fine-grained paraphrase types poses a significant challenge. While most approaches are good at generating and detecting general semantic similar content, they fail to understand the intrinsic linguistic variables they manipulate. Models trained in generating and identifying paraphrase types also show improvements in tasks without them. In addition, scaling these models further improves their ability to understand paraphrase types. We believe paraphrase types can unlock a new paradigm for developing paraphrase models and solving tasks in the future. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.14863v3-abstract-full').style.display = 'none'; document.getElementById('2310.14863v3-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 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">Published at EMNLP 2023</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> EMNLP 2023 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.16143">arXiv:2306.16143</a> <span> [<a href="https://arxiv.org/pdf/2306.16143">pdf</a>, <a href="https://arxiv.org/format/2306.16143">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Generative User-Experience Research for Developing Domain-specific Natural Language Processing Applications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhukova%2C+A">Anastasia Zhukova</a>, <a href="/search/cs?searchtype=author&query=von+Sperl%2C+L">Lukas von Sperl</a>, <a href="/search/cs?searchtype=author&query=Matt%2C+C+E">Christian E. Matt</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2306.16143v5-abstract-short" style="display: inline;"> User experience (UX) is a part of human-computer interaction (HCI) research and focuses on increasing intuitiveness, transparency, simplicity, and trust for the system users. Most UX research for machine learning (ML) or natural language processing (NLP) focuses on a data-driven methodology. It engages domain users mainly for usability evaluation. Moreover, more typical UX methods tailor the syste… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.16143v5-abstract-full').style.display = 'inline'; document.getElementById('2306.16143v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.16143v5-abstract-full" style="display: none;"> User experience (UX) is a part of human-computer interaction (HCI) research and focuses on increasing intuitiveness, transparency, simplicity, and trust for the system users. Most UX research for machine learning (ML) or natural language processing (NLP) focuses on a data-driven methodology. It engages domain users mainly for usability evaluation. Moreover, more typical UX methods tailor the systems towards user usability, unlike learning about the user needs first. This paper proposes a new methodology for integrating generative UX research into developing domain NLP applications. Generative UX research employs domain users at the initial stages of prototype development, i.e., ideation and concept evaluation, and the last stage for evaluating system usefulness and user utility. The methodology emerged from and is evaluated on a case study about the full-cycle prototype development of a domain-specific semantic search for daily operations in the process industry. A key finding of our case study is that involving domain experts increases their interest and trust in the final NLP application. The combined UX+NLP research of the proposed method efficiently considers data- and user-driven opportunities and constraints, which can be crucial for developing NLP applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.16143v5-abstract-full').style.display = 'none'; document.getElementById('2306.16143v5-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 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/2305.16433">arXiv:2305.16433</a> <span> [<a href="https://arxiv.org/pdf/2305.16433">pdf</a>, <a href="https://arxiv.org/format/2305.16433">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="Symbolic Computation">cs.SC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> </div> </div> <p class="title is-5 mathjax"> Neural Machine Translation for Mathematical Formulae </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Petersen%2C+F">Felix Petersen</a>, <a href="/search/cs?searchtype=author&query=Schubotz%2C+M">Moritz Schubotz</a>, <a href="/search/cs?searchtype=author&query=Greiner-Petter%2C+A">Andre Greiner-Petter</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2305.16433v1-abstract-short" style="display: inline;"> We tackle the problem of neural machine translation of mathematical formulae between ambiguous presentation languages and unambiguous content languages. Compared to neural machine translation on natural language, mathematical formulae have a much smaller vocabulary and much longer sequences of symbols, while their translation requires extreme precision to satisfy mathematical information needs. In… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.16433v1-abstract-full').style.display = 'inline'; document.getElementById('2305.16433v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.16433v1-abstract-full" style="display: none;"> We tackle the problem of neural machine translation of mathematical formulae between ambiguous presentation languages and unambiguous content languages. Compared to neural machine translation on natural language, mathematical formulae have a much smaller vocabulary and much longer sequences of symbols, while their translation requires extreme precision to satisfy mathematical information needs. In this work, we perform the tasks of translating from LaTeX to Mathematica as well as from LaTeX to semantic LaTeX. While recurrent, recursive, and transformer networks struggle with preserving all contained information, we find that convolutional sequence-to-sequence networks achieve 95.1% and 90.7% exact matches, respectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.16433v1-abstract-full').style.display = 'none'; document.getElementById('2305.16433v1-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 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">Published at ACL 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/2305.13193">arXiv:2305.13193</a> <span> [<a href="https://arxiv.org/pdf/2305.13193">pdf</a>, <a href="https://arxiv.org/format/2305.13193">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> TEIMMA: The First Content Reuse Annotator for Text, Images, and Math </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Satpute%2C+A">Ankit Satpute</a>, <a href="/search/cs?searchtype=author&query=Greiner-Petter%2C+A">Andr茅 Greiner-Petter</a>, <a href="/search/cs?searchtype=author&query=Schubotz%2C+M">Moritz Schubotz</a>, <a href="/search/cs?searchtype=author&query=Meuschke%2C+N">Norman Meuschke</a>, <a href="/search/cs?searchtype=author&query=Aizawa%2C+A">Akiko Aizawa</a>, <a href="/search/cs?searchtype=author&query=Teschke%2C+O">Olaf Teschke</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2305.13193v2-abstract-short" style="display: inline;"> This demo paper presents the first tool to annotate the reuse of text, images, and mathematical formulae in a document pair -- TEIMMA. Annotating content reuse is particularly useful to develop plagiarism detection algorithms. Real-world content reuse is often obfuscated, which makes it challenging to identify such cases. TEIMMA allows entering the obfuscation type to enable novel classifications… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.13193v2-abstract-full').style.display = 'inline'; document.getElementById('2305.13193v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.13193v2-abstract-full" style="display: none;"> This demo paper presents the first tool to annotate the reuse of text, images, and mathematical formulae in a document pair -- TEIMMA. Annotating content reuse is particularly useful to develop plagiarism detection algorithms. Real-world content reuse is often obfuscated, which makes it challenging to identify such cases. TEIMMA allows entering the obfuscation type to enable novel classifications for confirmed cases of plagiarism. It enables recording different reuse types for text, images, and mathematical formulae in HTML and supports users by visualizing the content reuse in a document pair using similarity detection methods for text and math. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.13193v2-abstract-full').style.display = 'none'; document.getElementById('2305.13193v2-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 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.07335">arXiv:2305.07335</a> <span> [<a href="https://arxiv.org/pdf/2305.07335">pdf</a>, <a href="https://arxiv.org/format/2305.07335">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</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/10.5281/zenodo.7924634">10.5281/zenodo.7924634 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Methods and Tools to Advance the Retrieval of Mathematical Knowledge from Digital Libraries for Search-, Recommendation-, and Assistance-Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Greiner-Petter%2C+A">Andr茅 Greiner-Petter</a>, <a href="/search/cs?searchtype=author&query=Schubotz%2C+M">Moritz Schubotz</a>, <a href="/search/cs?searchtype=author&query=Meuschke%2C+N">Norman Meuschke</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="2305.07335v1-abstract-short" style="display: inline;"> This project investigated new approaches and technologies to enhance the accessibility of mathematical content and its semantic information for a broad range of information retrieval applications. To achieve this goal, the project addressed three main research challenges: (1) syntactic analysis of mathematical expressions, (2) semantic enrichment of mathematical expressions, and (3) evaluation usi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.07335v1-abstract-full').style.display = 'inline'; document.getElementById('2305.07335v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.07335v1-abstract-full" style="display: none;"> This project investigated new approaches and technologies to enhance the accessibility of mathematical content and its semantic information for a broad range of information retrieval applications. To achieve this goal, the project addressed three main research challenges: (1) syntactic analysis of mathematical expressions, (2) semantic enrichment of mathematical expressions, and (3) evaluation using quality metrics and demonstrators. To make our research useful for the research community, we published tools that enable researchers to process mathematical expressions more effectively and efficiently. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.07335v1-abstract-full').style.display = 'none'; document.getElementById('2305.07335v1-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 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">The final report for the DFG-Project MathIR - July 1st, 2018 - December 31st, 2022</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> GI 1259-1 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.3.0 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.02049">arXiv:2305.02049</a> <span> [<a href="https://arxiv.org/pdf/2305.02049">pdf</a>, <a href="https://arxiv.org/format/2305.02049">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</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/10.23919/IFIPNetworking52078.2021.9472842">10.23919/IFIPNetworking52078.2021.9472842 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Introducing Peer Copy -- A Fully Decentralized Peer-to-Peer File Transfer Tool </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Trautwein%2C+D">Dennis Trautwein</a>, <a href="/search/cs?searchtype=author&query=Schubotz%2C+M">Moritz Schubotz</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2305.02049v1-abstract-short" style="display: inline;"> It allows any two parties that are either both on the same network or connected via the internet to transfer the contents of a file based on a particular sequence of words. Peer discovery happens via multicast DNS if both peers are on the same network or via entries in the distributed hash table (DHT) of the InterPlanetary File-System (IPFS) if both peers are connected across network boundaries. A… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.02049v1-abstract-full').style.display = 'inline'; document.getElementById('2305.02049v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.02049v1-abstract-full" style="display: none;"> It allows any two parties that are either both on the same network or connected via the internet to transfer the contents of a file based on a particular sequence of words. Peer discovery happens via multicast DNS if both peers are on the same network or via entries in the distributed hash table (DHT) of the InterPlanetary File-System (IPFS) if both peers are connected across network boundaries. As soon as a connection is established, the word sequence is used as the input for a password-authenticated key exchange (PAKE) to derive a strong session key. This session key authenticates the peers and encrypts any subsequent communication. It is found that the decentralized approach to peer-to-peer file transfer can keep up with established centralized tools while eliminating the reliance on centralized service providers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.02049v1-abstract-full').style.display = 'none'; document.getElementById('2305.02049v1-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> 3 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> 2021 IFIP Networking Conference </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.13148">arXiv:2304.13148</a> <span> [<a href="https://arxiv.org/pdf/2304.13148">pdf</a>, <a href="https://arxiv.org/format/2304.13148">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</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/10.1145/3539618.3591882">10.1145/3539618.3591882 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Introducing MBIB -- the first Media Bias Identification Benchmark Task and Dataset Collection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wessel%2C+M">Martin Wessel</a>, <a href="/search/cs?searchtype=author&query=Horych%2C+T">Tom谩拧 Horych</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Aizawa%2C+A">Akiko Aizawa</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Spinde%2C+T">Timo Spinde</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="2304.13148v1-abstract-short" style="display: inline;"> Although media bias detection is a complex multi-task problem, there is, to date, no unified benchmark grouping these evaluation tasks. We introduce the Media Bias Identification Benchmark (MBIB), a comprehensive benchmark that groups different types of media bias (e.g., linguistic, cognitive, political) under a common framework to test how prospective detection techniques generalize. After review… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.13148v1-abstract-full').style.display = 'inline'; document.getElementById('2304.13148v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.13148v1-abstract-full" style="display: none;"> Although media bias detection is a complex multi-task problem, there is, to date, no unified benchmark grouping these evaluation tasks. We introduce the Media Bias Identification Benchmark (MBIB), a comprehensive benchmark that groups different types of media bias (e.g., linguistic, cognitive, political) under a common framework to test how prospective detection techniques generalize. After reviewing 115 datasets, we select nine tasks and carefully propose 22 associated datasets for evaluating media bias detection techniques. We evaluate MBIB using state-of-the-art Transformer techniques (e.g., T5, BART). Our results suggest that while hate speech, racial bias, and gender bias are easier to detect, models struggle to handle certain bias types, e.g., cognitive and political bias. However, our results show that no single technique can outperform all the others significantly. We also find an uneven distribution of research interest and resource allocation to the individual tasks in media bias. A unified benchmark encourages the development of more robust systems and shifts the current paradigm in media bias detection evaluation towards solutions that tackle not one but multiple media bias types simultaneously. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.13148v1-abstract-full').style.display = 'none'; document.getElementById('2304.13148v1-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 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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">To be published in Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '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/2303.13989">arXiv:2303.13989</a> <span> [<a href="https://arxiv.org/pdf/2303.13989">pdf</a>, <a href="https://arxiv.org/format/2303.13989">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> <p class="title is-5 mathjax"> Paraphrase Detection: Human vs. Machine Content </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Becker%2C+J">Jonas Becker</a>, <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2303.13989v1-abstract-short" style="display: inline;"> The growing prominence of large language models, such as GPT-4 and ChatGPT, has led to increased concerns over academic integrity due to the potential for machine-generated content and paraphrasing. Although studies have explored the detection of human- and machine-paraphrased content, the comparison between these types of content remains underexplored. In this paper, we conduct a comprehensive an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.13989v1-abstract-full').style.display = 'inline'; document.getElementById('2303.13989v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.13989v1-abstract-full" style="display: none;"> The growing prominence of large language models, such as GPT-4 and ChatGPT, has led to increased concerns over academic integrity due to the potential for machine-generated content and paraphrasing. Although studies have explored the detection of human- and machine-paraphrased content, the comparison between these types of content remains underexplored. In this paper, we conduct a comprehensive analysis of various datasets commonly employed for paraphrase detection tasks and evaluate an array of detection methods. Our findings highlight the strengths and limitations of different detection methods in terms of performance on individual datasets, revealing a lack of suitable machine-generated datasets that can be aligned with human expectations. Our main finding is that human-authored paraphrases exceed machine-generated ones in terms of difficulty, diversity, and similarity implying that automatically generated texts are not yet on par with human-level performance. Transformers emerged as the most effective method across datasets with TF-IDF excelling on semantically diverse corpora. Additionally, we identify four datasets as the most diverse and challenging for paraphrase detection. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.13989v1-abstract-full').style.display = 'none'; document.getElementById('2303.13989v1-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> 24 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.09957">arXiv:2303.09957</a> <span> [<a href="https://arxiv.org/pdf/2303.09957">pdf</a>, <a href="https://arxiv.org/format/2303.09957">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</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/10.1007/978-3-031-28032-0_31">10.1007/978-3-031-28032-0_31 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Benchmark of PDF Information Extraction Tools using a Multi-Task and Multi-Domain Evaluation Framework for Academic Documents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Meuschke%2C+N">Norman Meuschke</a>, <a href="/search/cs?searchtype=author&query=Jagdale%2C+A">Apurva Jagdale</a>, <a href="/search/cs?searchtype=author&query=Spinde%2C+T">Timo Spinde</a>, <a href="/search/cs?searchtype=author&query=Mitrovi%C4%87%2C+J">Jelena Mitrovi膰</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2303.09957v1-abstract-short" style="display: inline;"> Extracting information from academic PDF documents is crucial for numerous indexing, retrieval, and analysis use cases. Choosing the best tool to extract specific content elements is difficult because many, technically diverse tools are available, but recent performance benchmarks are rare. Moreover, such benchmarks typically cover only a few content elements like header metadata or bibliographic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.09957v1-abstract-full').style.display = 'inline'; document.getElementById('2303.09957v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.09957v1-abstract-full" style="display: none;"> Extracting information from academic PDF documents is crucial for numerous indexing, retrieval, and analysis use cases. Choosing the best tool to extract specific content elements is difficult because many, technically diverse tools are available, but recent performance benchmarks are rare. Moreover, such benchmarks typically cover only a few content elements like header metadata or bibliographic references and use smaller datasets from specific academic disciplines. We provide a large and diverse evaluation framework that supports more extraction tasks than most related datasets. Our framework builds upon DocBank, a multi-domain dataset of 1.5M annotated content elements extracted from 500K pages of research papers on arXiv. Using the new framework, we benchmark ten freely available tools in extracting document metadata, bibliographic references, tables, and other content elements from academic PDF documents. GROBID achieves the best metadata and reference extraction results, followed by CERMINE and Science Parse. For table extraction, Adobe Extract outperforms other tools, even though the performance is much lower than for other content elements. All tools struggle to extract lists, footers, and equations. We conclude that more research on improving and combining tools is necessary to achieve satisfactory extraction quality for most content elements. Evaluation datasets and frameworks like the one we present support this line of research. We make our data and code publicly available to contribute toward this goal. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.09957v1-abstract-full').style.display = 'none'; document.getElementById('2303.09957v1-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> 17 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">iConference 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/2303.03886">arXiv:2303.03886</a> <span> [<a href="https://arxiv.org/pdf/2303.03886">pdf</a>, <a href="https://arxiv.org/format/2303.03886">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> AI Usage Cards: Responsibly Reporting AI-generated Content </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Mohammad%2C+S+M">Saif M. Mohammad</a>, <a href="/search/cs?searchtype=author&query=Meuschke%2C+N">Norman Meuschke</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2303.03886v2-abstract-short" style="display: inline;"> Given AI systems like ChatGPT can generate content that is indistinguishable from human-made work, the responsible use of this technology is a growing concern. Although understanding the benefits and harms of using AI systems requires more time, their rapid and indiscriminate adoption in practice is a reality. Currently, we lack a common framework and language to define and report the responsible… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.03886v2-abstract-full').style.display = 'inline'; document.getElementById('2303.03886v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.03886v2-abstract-full" style="display: none;"> Given AI systems like ChatGPT can generate content that is indistinguishable from human-made work, the responsible use of this technology is a growing concern. Although understanding the benefits and harms of using AI systems requires more time, their rapid and indiscriminate adoption in practice is a reality. Currently, we lack a common framework and language to define and report the responsible use of AI for content generation. Prior work proposed guidelines for using AI in specific scenarios (e.g., robotics or medicine) which are not transferable to conducting and reporting scientific research. Our work makes two contributions: First, we propose a three-dimensional model consisting of transparency, integrity, and accountability to define the responsible use of AI. Second, we introduce ``AI Usage Cards'', a standardized way to report the use of AI in scientific research. Our model and cards allow users to reflect on key principles of responsible AI usage. They also help the research community trace, compare, and question various forms of AI usage and support the development of accepted community norms. The proposed framework and reporting system aims to promote the ethical and responsible use of AI in scientific research and provide a standardized approach for reporting AI usage across different research fields. We also provide a free service to easily generate AI Usage Cards for scientific work via a questionnaire and export them in various machine-readable formats for inclusion in different work products at https://ai-cards.org. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.03886v2-abstract-full').style.display = 'none'; document.getElementById('2303.03886v2-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 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.01994">arXiv:2303.01994</a> <span> [<a href="https://arxiv.org/pdf/2303.01994">pdf</a>, <a href="https://arxiv.org/format/2303.01994">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Discovery and Recognition of Formula Concepts using Machine Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Scharpf%2C+P">Philipp Scharpf</a>, <a href="/search/cs?searchtype=author&query=Schubotz%2C+M">Moritz Schubotz</a>, <a href="/search/cs?searchtype=author&query=Cohl%2C+H+S">Howard S. Cohl</a>, <a href="/search/cs?searchtype=author&query=Breitinger%2C+C">Corinna Breitinger</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2303.01994v2-abstract-short" style="display: inline;"> Citation-based Information Retrieval (IR) methods for scientific documents have proven effective for IR applications, such as Plagiarism Detection or Literature Recommender Systems in academic disciplines that use many references. In science, technology, engineering, and mathematics, researchers often employ mathematical concepts through formula notation to refer to prior knowledge. Our long-term… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.01994v2-abstract-full').style.display = 'inline'; document.getElementById('2303.01994v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.01994v2-abstract-full" style="display: none;"> Citation-based Information Retrieval (IR) methods for scientific documents have proven effective for IR applications, such as Plagiarism Detection or Literature Recommender Systems in academic disciplines that use many references. In science, technology, engineering, and mathematics, researchers often employ mathematical concepts through formula notation to refer to prior knowledge. Our long-term goal is to generalize citation-based IR methods and apply this generalized method to both classical references and mathematical concepts. In this paper, we suggest how mathematical formulas could be cited and define a Formula Concept Retrieval task with two subtasks: Formula Concept Discovery (FCD) and Formula Concept Recognition (FCR). While FCD aims at the definition and exploration of a 'Formula Concept' that names bundled equivalent representations of a formula, FCR is designed to match a given formula to a prior assigned unique mathematical concept identifier. We present machine learning-based approaches to address the FCD and FCR tasks. We then evaluate these approaches on a standardized test collection (NTCIR arXiv dataset). Our FCD approach yields a precision of 68% for retrieving equivalent representations of frequent formulas and a recall of 72% for extracting the formula name from the surrounding text. FCD and FCR enable the citation of formulas within mathematical documents and facilitate semantic search and question answering as well as document similarity assessments for plagiarism detection or recommender systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.01994v2-abstract-full').style.display = 'none'; document.getElementById('2303.01994v2-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> 19 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 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 by Scientometrics (Springer) journal</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68P20 (Primary); 68T50 (Secondary) <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.3.3; I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.08361">arXiv:2211.08361</a> <span> [<a href="https://arxiv.org/pdf/2211.08361">pdf</a>, <a href="https://arxiv.org/format/2211.08361">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</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/10.13140/RG.2.2.30988.18568">10.13140/RG.2.2.30988.18568 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Collaborative and AI-aided Exam Question Generation using Wikidata in Education </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Scharpf%2C+P">Philipp Scharpf</a>, <a href="/search/cs?searchtype=author&query=Schubotz%2C+M">Moritz Schubotz</a>, <a href="/search/cs?searchtype=author&query=Spitz%2C+A">Andreas Spitz</a>, <a href="/search/cs?searchtype=author&query=Greiner-Petter%2C+A">Andre Greiner-Petter</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2211.08361v1-abstract-short" style="display: inline;"> Since the COVID-19 outbreak, the use of digital learning or education platforms has significantly increased. Teachers now digitally distribute homework and provide exercise questions. In both cases, teachers need to continuously develop novel and individual questions. This process can be very time-consuming and should be facilitated and accelerated both through exchange with other teachers and by… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.08361v1-abstract-full').style.display = 'inline'; document.getElementById('2211.08361v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.08361v1-abstract-full" style="display: none;"> Since the COVID-19 outbreak, the use of digital learning or education platforms has significantly increased. Teachers now digitally distribute homework and provide exercise questions. In both cases, teachers need to continuously develop novel and individual questions. This process can be very time-consuming and should be facilitated and accelerated both through exchange with other teachers and by using Artificial Intelligence (AI) capabilities. To address this need, we propose a multilingual Wikimedia framework that allows for collaborative worldwide teacher knowledge engineering and subsequent AI-aided question generation, test, and correction. As a proof of concept, we present >>PhysWikiQuiz<<, a physics question generation and test engine. Our system (hosted by Wikimedia at https://physwikiquiz.wmflabs.org) retrieves physics knowledge from the open community-curated database Wikidata. It can generate questions in different variations and verify answer values and units using a Computer Algebra System (CAS). We evaluate the performance on a public benchmark dataset at each stage of the system workflow. For an average formula with three variables, the system can generate and correct up to 300 questions for individual students based on a single formula concept name as input by the teacher. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.08361v1-abstract-full').style.display = 'none'; document.getElementById('2211.08361v1-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 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68Uxx <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.4 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.06664">arXiv:2211.06664</a> <span> [<a href="https://arxiv.org/pdf/2211.06664">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Mining Mathematical Documents for Question Answering via Unsupervised Formula Labeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Scharpf%2C+P">Philipp Scharpf</a>, <a href="/search/cs?searchtype=author&query=Schubotz%2C+M">Moritz Schubotz</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2211.06664v1-abstract-short" style="display: inline;"> The increasing number of questions on Question Answering (QA) platforms like Math Stack Exchange (MSE) signifies a growing information need to answer math-related questions. However, there is currently very little research on approaches for an open data QA system that retrieves mathematical formulae using their concept names or querying formula identifier relationships from knowledge graphs. In th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.06664v1-abstract-full').style.display = 'inline'; document.getElementById('2211.06664v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.06664v1-abstract-full" style="display: none;"> The increasing number of questions on Question Answering (QA) platforms like Math Stack Exchange (MSE) signifies a growing information need to answer math-related questions. However, there is currently very little research on approaches for an open data QA system that retrieves mathematical formulae using their concept names or querying formula identifier relationships from knowledge graphs. In this paper, we aim to bridge the gap by presenting data mining methods and benchmark results to employ Mathematical Entity Linking (MathEL) and Unsupervised Formula Labeling (UFL) for semantic formula search and mathematical question answering (MathQA) on the arXiv preprint repository, Wikipedia, and Wikidata, which is part of the Wikimedia ecosystem of free knowledge. Based on different types of information needs, we evaluate our system in 15 information need modes, assessing over 7,000 query results. Furthermore, we compare its performance to a commercial knowledge-base and calculation-engine (Wolfram Alpha) and search-engine (Google). The open source system is hosted by Wikimedia at https://mathqa.wmflabs.org. A demovideo is available at purl.org/mathqa. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.06664v1-abstract-full').style.display = 'none'; document.getElementById('2211.06664v1-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 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68Uxx <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.4 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.04049">arXiv:2211.04049</a> <span> [<a href="https://arxiv.org/pdf/2211.04049">pdf</a>, <a href="https://arxiv.org/ps/2211.04049">ps</a>, <a href="https://arxiv.org/format/2211.04049">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</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/10.3389/frma.2022.861944">10.3389/frma.2022.861944 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Caching and Reproducibility: Making Data Science experiments faster and FAIRer </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Schubotz%2C+M">Moritz Schubotz</a>, <a href="/search/cs?searchtype=author&query=Satpute%2C+A">Ankit Satpute</a>, <a href="/search/cs?searchtype=author&query=Greiner-Petter%2C+A">Andre Greiner-Petter</a>, <a href="/search/cs?searchtype=author&query=Aizawa%2C+A">Akiko Aizawa</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2211.04049v2-abstract-short" style="display: inline;"> Small to medium-scale data science experiments often rely on research software developed ad-hoc by individual scientists or small teams. Often there is no time to make the research software fast, reusable, and open access. The consequence is twofold. First, subsequent researchers must spend significant work hours building upon the proposed hypotheses or experimental framework. In the worst case, o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.04049v2-abstract-full').style.display = 'inline'; document.getElementById('2211.04049v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.04049v2-abstract-full" style="display: none;"> Small to medium-scale data science experiments often rely on research software developed ad-hoc by individual scientists or small teams. Often there is no time to make the research software fast, reusable, and open access. The consequence is twofold. First, subsequent researchers must spend significant work hours building upon the proposed hypotheses or experimental framework. In the worst case, others cannot reproduce the experiment and reuse the findings for subsequent research. Second, suppose the ad-hoc research software fails during often long-running computationally expensive experiments. In that case, the overall effort to iteratively improve the software and rerun the experiments creates significant time pressure on the researchers. We suggest making caching an integral part of the research software development process, even before the first line of code is written. This article outlines caching recommendations for developing research software in data science projects. Our recommendations provide a perspective to circumvent common problems such as propriety dependence, speed, etc. At the same time, caching contributes to the reproducibility of experiments in the open science workflow. Concerning the four guiding principles, i.e., Findability, Accessibility, Interoperability, and Reusability (FAIR), we foresee that including the proposed recommendation in a research software development will make the data related to that software FAIRer for both machines and humans. We exhibit the usefulness of some of the proposed recommendations on our recently completed research software project in mathematical information retrieval. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.04049v2-abstract-full').style.display = 'none'; document.getElementById('2211.04049v2-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 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">8 pages, 1 table</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Frontiers in Research Metrics and Analytics, volume 7, 2022 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.03491">arXiv:2211.03491</a> <span> [<a href="https://arxiv.org/pdf/2211.03491">pdf</a>, <a href="https://arxiv.org/format/2211.03491">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/10.1007/978-3-030-96957-8_20">10.1007/978-3-030-96957-8_20 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Exploiting Transformer-based Multitask Learning for the Detection of Media Bias in News Articles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Spinde%2C+T">Timo Spinde</a>, <a href="/search/cs?searchtype=author&query=Krieger%2C+J">Jan-David Krieger</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Mitrovi%C4%87%2C+J">Jelena Mitrovi膰</a>, <a href="/search/cs?searchtype=author&query=G%C3%B6tz-Hahn%2C+F">Franz G枚tz-Hahn</a>, <a href="/search/cs?searchtype=author&query=Aizawa%2C+A">Akiko Aizawa</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2211.03491v1-abstract-short" style="display: inline;"> Media has a substantial impact on the public perception of events. A one-sided or polarizing perspective on any topic is usually described as media bias. One of the ways how bias in news articles can be introduced is by altering word choice. Biased word choices are not always obvious, nor do they exhibit high context-dependency. Hence, detecting bias is often difficult. We propose a Transformer-ba… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.03491v1-abstract-full').style.display = 'inline'; document.getElementById('2211.03491v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.03491v1-abstract-full" style="display: none;"> Media has a substantial impact on the public perception of events. A one-sided or polarizing perspective on any topic is usually described as media bias. One of the ways how bias in news articles can be introduced is by altering word choice. Biased word choices are not always obvious, nor do they exhibit high context-dependency. Hence, detecting bias is often difficult. We propose a Transformer-based deep learning architecture trained via Multi-Task Learning using six bias-related data sets to tackle the media bias detection problem. Our best-performing implementation achieves a macro $F_{1}$ of 0.776, a performance boost of 3\% compared to our baseline, outperforming existing methods. Our results indicate Multi-Task Learning as a promising alternative to improve existing baseline models in identifying slanted reporting. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.03491v1-abstract-full').style.display = 'none'; document.getElementById('2211.03491v1-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> 7 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proceedings of the iConference 2022 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.14606">arXiv:2210.14606</a> <span> [<a href="https://arxiv.org/pdf/2210.14606">pdf</a>, <a href="https://arxiv.org/format/2210.14606">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/10.18653/v1/2022.gem-1.5">10.18653/v1/2022.gem-1.5 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Analyzing Multi-Task Learning for Abstractive Text Summarization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kirstein%2C+F">Frederic Kirstein</a>, <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2210.14606v2-abstract-short" style="display: inline;"> Despite the recent success of multi-task learning and pre-finetuning for natural language understanding, few works have studied the effects of task families on abstractive text summarization. Task families are a form of task grouping during the pre-finetuning stage to learn common skills, such as reading comprehension. To close this gap, we analyze the influence of multi-task learning strategies u… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.14606v2-abstract-full').style.display = 'inline'; document.getElementById('2210.14606v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.14606v2-abstract-full" style="display: none;"> Despite the recent success of multi-task learning and pre-finetuning for natural language understanding, few works have studied the effects of task families on abstractive text summarization. Task families are a form of task grouping during the pre-finetuning stage to learn common skills, such as reading comprehension. To close this gap, we analyze the influence of multi-task learning strategies using task families for the English abstractive text summarization task. We group tasks into one of three strategies, i.e., sequential, simultaneous, and continual multi-task learning, and evaluate trained models through two downstream tasks. We find that certain combinations of task families (e.g., advanced reading comprehension and natural language inference) positively impact downstream performance. Further, we find that choice and combinations of task families influence downstream performance more than the training scheme, supporting the use of task families for abstractive text summarization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.14606v2-abstract-full').style.display = 'none'; document.getElementById('2210.14606v2-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 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> EMNLP-GEM 2022 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.06878">arXiv:2210.06878</a> <span> [<a href="https://arxiv.org/pdf/2210.06878">pdf</a>, <a href="https://arxiv.org/format/2210.06878">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="Digital Libraries">cs.DL</span> </div> </div> <p class="title is-5 mathjax"> CS-Insights: A System for Analyzing Computer Science Research </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=K%C3%BCll%2C+L">Lennart K眉ll</a>, <a href="/search/cs?searchtype=author&query=Mohammad%2C+S+M">Saif M. Mohammad</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2210.06878v2-abstract-short" style="display: inline;"> This paper presents CS-Insights, an interactive web application to analyze computer science publications from DBLP through multiple perspectives. The dedicated interfaces allow its users to identify trends in research activity, productivity, accessibility, author's productivity, venues' statistics, topics of interest, and the impact of computer science research on other fields. CS-Insightsis publi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.06878v2-abstract-full').style.display = 'inline'; document.getElementById('2210.06878v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.06878v2-abstract-full" style="display: none;"> This paper presents CS-Insights, an interactive web application to analyze computer science publications from DBLP through multiple perspectives. The dedicated interfaces allow its users to identify trends in research activity, productivity, accessibility, author's productivity, venues' statistics, topics of interest, and the impact of computer science research on other fields. CS-Insightsis publicly available, and its modular architecture can be easily adapted to domains other than computer science. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.06878v2-abstract-full').style.display = 'none'; document.getElementById('2210.06878v2-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> 29 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.03568">arXiv:2210.03568</a> <span> [<a href="https://arxiv.org/pdf/2210.03568">pdf</a>, <a href="https://arxiv.org/format/2210.03568">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/10.18653/v1/2022.emnlp-main.62">10.18653/v1/2022.emnlp-main.62 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> How Large Language Models are Transforming Machine-Paraphrased Plagiarism </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Kirstein%2C+F">Frederic Kirstein</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2210.03568v3-abstract-short" style="display: inline;"> The recent success of large language models for text generation poses a severe threat to academic integrity, as plagiarists can generate realistic paraphrases indistinguishable from original work. However, the role of large autoregressive transformers in generating machine-paraphrased plagiarism and their detection is still developing in the literature. This work explores T5 and GPT-3 for machine-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.03568v3-abstract-full').style.display = 'inline'; document.getElementById('2210.03568v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.03568v3-abstract-full" style="display: none;"> The recent success of large language models for text generation poses a severe threat to academic integrity, as plagiarists can generate realistic paraphrases indistinguishable from original work. However, the role of large autoregressive transformers in generating machine-paraphrased plagiarism and their detection is still developing in the literature. This work explores T5 and GPT-3 for machine-paraphrase generation on scientific articles from arXiv, student theses, and Wikipedia. We evaluate the detection performance of six automated solutions and one commercial plagiarism detection software and perform a human study with 105 participants regarding their detection performance and the quality of generated examples. Our results suggest that large models can rewrite text humans have difficulty identifying as machine-paraphrased (53% mean acc.). Human experts rate the quality of paraphrases generated by GPT-3 as high as original texts (clarity 4.0/5, fluency 4.2/5, coherence 3.8/5). The best-performing detection model (GPT-3) achieves a 66% F1-score in detecting paraphrases. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.03568v3-abstract-full').style.display = 'none'; document.getElementById('2210.03568v3-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 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> EMNLP 2022 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.14557">arXiv:2209.14557</a> <span> [<a href="https://arxiv.org/pdf/2209.14557">pdf</a>, <a href="https://arxiv.org/format/2209.14557">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/10.18653/v1/2021.findings-emnlp.101">10.18653/v1/2021.findings-emnlp.101 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Spinde%2C+T">Timo Spinde</a>, <a href="/search/cs?searchtype=author&query=Plank%2C+M">Manuel Plank</a>, <a href="/search/cs?searchtype=author&query=Krieger%2C+J">Jan-David Krieger</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Aizawa%2C+A">Akiko Aizawa</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="2209.14557v1-abstract-short" style="display: inline;"> Media coverage has a substantial effect on the public perception of events. Nevertheless, media outlets are often biased. One way to bias news articles is by altering the word choice. The automatic identification of bias by word choice is challenging, primarily due to the lack of a gold standard data set and high context dependencies. This paper presents BABE, a robust and diverse data set created… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.14557v1-abstract-full').style.display = 'inline'; document.getElementById('2209.14557v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.14557v1-abstract-full" style="display: none;"> Media coverage has a substantial effect on the public perception of events. Nevertheless, media outlets are often biased. One way to bias news articles is by altering the word choice. The automatic identification of bias by word choice is challenging, primarily due to the lack of a gold standard data set and high context dependencies. This paper presents BABE, a robust and diverse data set created by trained experts, for media bias research. We also analyze why expert labeling is essential within this domain. Our data set offers better annotation quality and higher inter-annotator agreement than existing work. It consists of 3,700 sentences balanced among topics and outlets, containing media bias labels on the word and sentence level. Based on our data, we also introduce a way to detect bias-inducing sentences in news articles automatically. Our best performing BERT-based model is pre-trained on a larger corpus consisting of distant labels. Fine-tuning and evaluating the model on our proposed supervised data set, we achieve a macro F1-score of 0.804, outperforming existing methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.14557v1-abstract-full').style.display = 'none'; document.getElementById('2209.14557v1-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> 29 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">substantial text overlap with Ph.D. proposal by same author, part of dissertation arXiv:2112.13352</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Findings of the Association for Computational Linguistics: EMNLP 2021 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.05877">arXiv:2208.05877</a> <span> [<a href="https://arxiv.org/pdf/2208.05877">pdf</a>, <a href="https://arxiv.org/format/2208.05877">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</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/10.1145/3544216.3544232">10.1145/3544216.3544232 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Design and Evaluation of IPFS: A Storage Layer for the Decentralized Web </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Trautwein%2C+D">Dennis Trautwein</a>, <a href="/search/cs?searchtype=author&query=Raman%2C+A">Aravindh Raman</a>, <a href="/search/cs?searchtype=author&query=Tyson%2C+G">Gareth Tyson</a>, <a href="/search/cs?searchtype=author&query=Castro%2C+I">Ignacio Castro</a>, <a href="/search/cs?searchtype=author&query=Scott%2C+W">Will Scott</a>, <a href="/search/cs?searchtype=author&query=Schubotz%2C+M">Moritz Schubotz</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Psaras%2C+Y">Yiannis Psaras</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="2208.05877v1-abstract-short" style="display: inline;"> Recent years have witnessed growing consolidation of web operations. For example, the majority of web traffic now originates from a few organizations, and even micro-websites often choose to host on large pre-existing cloud infrastructures. In response to this, the "Decentralized Web" attempts to distribute ownership and operation of web services more evenly. This paper describes the design and im… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.05877v1-abstract-full').style.display = 'inline'; document.getElementById('2208.05877v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.05877v1-abstract-full" style="display: none;"> Recent years have witnessed growing consolidation of web operations. For example, the majority of web traffic now originates from a few organizations, and even micro-websites often choose to host on large pre-existing cloud infrastructures. In response to this, the "Decentralized Web" attempts to distribute ownership and operation of web services more evenly. This paper describes the design and implementation of the largest and most widely used Decentralized Web platform - the InterPlanetary File System (IPFS) - an open-source, content-addressable peer-to-peer network that provides distributed data storage and delivery. IPFS has millions of daily content retrievals and already underpins dozens of third-party applications. This paper evaluates the performance of IPFS by introducing a set of measurement methodologies that allow us to uncover the characteristics of peers in the IPFS network. We reveal presence in more than 2700 Autonomous Systems and 152 countries, the majority of which operate outside large central cloud providers like Amazon or Azure. We further evaluate IPFS performance, showing that both publication and retrieval delays are acceptable for a wide range of use cases. Finally, we share our datasets, experiences and lessons learned. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.05877v1-abstract-full').style.display = 'none'; document.getElementById('2208.05877v1-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 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">14 pages, 11 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> C.2.2; C.2.1 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> SIGCOMM '22, August 22-26, 2022, Amsterdam, Netherlands </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.10773">arXiv:2205.10773</a> <span> [<a href="https://arxiv.org/pdf/2205.10773">pdf</a>, <a href="https://arxiv.org/format/2205.10773">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">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/10.1145/3529372.3530932">10.1145/3529372.3530932 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Domain-adaptive Pre-training Approach for Language Bias Detection in News </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Krieger%2C+J">Jan-David Krieger</a>, <a href="/search/cs?searchtype=author&query=Spinde%2C+T">Timo Spinde</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Kulshrestha%2C+J">Juhi Kulshrestha</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2205.10773v1-abstract-short" style="display: inline;"> Media bias is a multi-faceted construct influencing individual behavior and collective decision-making. Slanted news reporting is the result of one-sided and polarized writing which can occur in various forms. In this work, we focus on an important form of media bias, i.e. bias by word choice. Detecting biased word choices is a challenging task due to its linguistic complexity and the lack of repr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.10773v1-abstract-full').style.display = 'inline'; document.getElementById('2205.10773v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.10773v1-abstract-full" style="display: none;"> Media bias is a multi-faceted construct influencing individual behavior and collective decision-making. Slanted news reporting is the result of one-sided and polarized writing which can occur in various forms. In this work, we focus on an important form of media bias, i.e. bias by word choice. Detecting biased word choices is a challenging task due to its linguistic complexity and the lack of representative gold-standard corpora. We present DA-RoBERTa, a new state-of-the-art transformer-based model adapted to the media bias domain which identifies sentence-level bias with an F1 score of 0.814. In addition, we also train, DA-BERT and DA-BART, two more transformer models adapted to the bias domain. Our proposed domain-adapted models outperform prior bias detection approaches on the same data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.10773v1-abstract-full').style.display = 'none'; document.getElementById('2205.10773v1-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 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proceedings of the ACM/IEEE-CS Joint Conference on Digital Libraries 2022 (JCDL) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2204.13384">arXiv:2204.13384</a> <span> [<a href="https://arxiv.org/pdf/2204.13384">pdf</a>, <a href="https://arxiv.org/format/2204.13384">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</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"> D3: A Massive Dataset of Scholarly Metadata for Analyzing the State of Computer Science Research </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wahle%2C+J+P">Jan Philip Wahle</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Mohammad%2C+S+M">Saif M. Mohammad</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2204.13384v4-abstract-short" style="display: inline;"> DBLP is the largest open-access repository of scientific articles on computer science and provides metadata associated with publications, authors, and venues. We retrieved more than 6 million publications from DBLP and extracted pertinent metadata (e.g., abstracts, author affiliations, citations) from the publication texts to create the DBLP Discovery Dataset (D3). D3 can be used to identify trend… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.13384v4-abstract-full').style.display = 'inline'; document.getElementById('2204.13384v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.13384v4-abstract-full" style="display: none;"> DBLP is the largest open-access repository of scientific articles on computer science and provides metadata associated with publications, authors, and venues. We retrieved more than 6 million publications from DBLP and extracted pertinent metadata (e.g., abstracts, author affiliations, citations) from the publication texts to create the DBLP Discovery Dataset (D3). D3 can be used to identify trends in research activity, productivity, focus, bias, accessibility, and impact of computer science research. We present an initial analysis focused on the volume of computer science research (e.g., number of papers, authors, research activity), trends in topics of interest, and citation patterns. Our findings show that computer science is a growing research field (approx. 15% annually), with an active and collaborative researcher community. While papers in recent years present more bibliographical entries in comparison to previous decades, the average number of citations has been declining. Investigating papers' abstracts reveals that recent topic trends are clearly reflected in D3. Finally, we list further applications of D3 and pose supplemental research questions. The D3 dataset, our findings, and source code are publicly available for research purposes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.13384v4-abstract-full').style.display = 'none'; document.getElementById('2204.13384v4-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 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> LREC 2022 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.14541">arXiv:2203.14541</a> <span> [<a href="https://arxiv.org/pdf/2203.14541">pdf</a>, <a href="https://arxiv.org/format/2203.14541">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</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"> Specialized Document Embeddings for Aspect-based Similarity of Research Papers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ostendorff%2C+M">Malte Ostendorff</a>, <a href="/search/cs?searchtype=author&query=Blume%2C+T">Till Blume</a>, <a href="/search/cs?searchtype=author&query=Ruas%2C+T">Terry Ruas</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Rehm%2C+G">Georg Rehm</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="2203.14541v1-abstract-short" style="display: inline;"> Document embeddings and similarity measures underpin content-based recommender systems, whereby a document is commonly represented as a single generic embedding. However, similarity computed on single vector representations provides only one perspective on document similarity that ignores which aspects make two documents alike. To address this limitation, aspect-based similarity measures have been… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.14541v1-abstract-full').style.display = 'inline'; document.getElementById('2203.14541v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.14541v1-abstract-full" style="display: none;"> Document embeddings and similarity measures underpin content-based recommender systems, whereby a document is commonly represented as a single generic embedding. However, similarity computed on single vector representations provides only one perspective on document similarity that ignores which aspects make two documents alike. To address this limitation, aspect-based similarity measures have been developed using document segmentation or pairwise multi-class document classification. While segmentation harms the document coherence, the pairwise classification approach scales poorly to large scale corpora. In this paper, we treat aspect-based similarity as a classical vector similarity problem in aspect-specific embedding spaces. We represent a document not as a single generic embedding but as multiple specialized embeddings. Our approach avoids document segmentation and scales linearly w.r.t.the corpus size. In an empirical study, we use the Papers with Code corpus containing 157,606 research papers and consider the task, method, and dataset of the respective research papers as their aspects. We compare and analyze three generic document embeddings, six specialized document embeddings and a pairwise classification baseline in the context of research paper recommendations. As generic document embeddings, we consider FastText, SciBERT, and SPECTER. To compute the specialized document embeddings, we compare three alternative methods inspired by retrofitting, fine-tuning, and Siamese networks. In our experiments, Siamese SciBERT achieved the highest scores. Additional analyses indicate an implicit bias of the generic document embeddings towards the dataset aspect and against the method aspect of each research paper. Our approach of aspect-based document embeddings mitigates potential risks arising from implicit biases by making them explicit. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.14541v1-abstract-full').style.display = 'none'; document.getElementById('2203.14541v1-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 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">Accepted for publication at JCDL 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2202.06671">arXiv:2202.06671</a> <span> [<a href="https://arxiv.org/pdf/2202.06671">pdf</a>, <a href="https://arxiv.org/format/2202.06671">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"> Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ostendorff%2C+M">Malte Ostendorff</a>, <a href="/search/cs?searchtype=author&query=Rethmeier%2C+N">Nils Rethmeier</a>, <a href="/search/cs?searchtype=author&query=Augenstein%2C+I">Isabelle Augenstein</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Rehm%2C+G">Georg Rehm</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="2202.06671v2-abstract-short" style="display: inline;"> Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics. Prior work relies on discrete citation relations to generate contrast samples. However, discrete citations enforce a hard cut-off to similarity. This is counter-i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.06671v2-abstract-full').style.display = 'inline'; document.getElementById('2202.06671v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.06671v2-abstract-full" style="display: none;"> Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics. Prior work relies on discrete citation relations to generate contrast samples. However, discrete citations enforce a hard cut-off to similarity. This is counter-intuitive to similarity-based learning, and ignores that scientific papers can be very similar despite lacking a direct citation - a core problem of finding related research. Instead, we use controlled nearest neighbor sampling over citation graph embeddings for contrastive learning. This control allows us to learn continuous similarity, to sample hard-to-learn negatives and positives, and also to avoid collisions between negative and positive samples by controlling the sampling margin between them. The resulting method SciNCL outperforms the state-of-the-art on the SciDocs benchmark. Furthermore, we demonstrate that it can train (or tune) models sample-efficiently, and that it can be combined with recent training-efficient methods. Perhaps surprisingly, even training a general-domain language model this way outperforms baselines pretrained in-domain. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.06671v2-abstract-full').style.display = 'none'; document.getElementById('2202.06671v2-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> 19 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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 to EMNLP 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.09488">arXiv:2201.09488</a> <span> [<a href="https://arxiv.org/pdf/2201.09488">pdf</a>, <a href="https://arxiv.org/format/2201.09488">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</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/10.1007/978-3-030-99524-9_5">10.1007/978-3-030-99524-9_5 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Comparative Verification of the Digital Library of Mathematical Functions and Computer Algebra Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Greiner-Petter%2C+A">Andr茅 Greiner-Petter</a>, <a href="/search/cs?searchtype=author&query=Cohl%2C+H+S">Howard S. Cohl</a>, <a href="/search/cs?searchtype=author&query=Youssef%2C+A">Abdou Youssef</a>, <a href="/search/cs?searchtype=author&query=Schubotz%2C+M">Moritz Schubotz</a>, <a href="/search/cs?searchtype=author&query=Trost%2C+A">Avi Trost</a>, <a href="/search/cs?searchtype=author&query=Dey%2C+R">Rajen Dey</a>, <a href="/search/cs?searchtype=author&query=Aizawa%2C+A">Akiko Aizawa</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2201.09488v2-abstract-short" style="display: inline;"> Digital mathematical libraries assemble the knowledge of years of mathematical research. Numerous disciplines (e.g., physics, engineering, pure and applied mathematics) rely heavily on compendia gathered findings. Likewise, modern research applications rely more and more on computational solutions, which are often calculated and verified by computer algebra systems. Hence, the correctness, accurac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.09488v2-abstract-full').style.display = 'inline'; document.getElementById('2201.09488v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.09488v2-abstract-full" style="display: none;"> Digital mathematical libraries assemble the knowledge of years of mathematical research. Numerous disciplines (e.g., physics, engineering, pure and applied mathematics) rely heavily on compendia gathered findings. Likewise, modern research applications rely more and more on computational solutions, which are often calculated and verified by computer algebra systems. Hence, the correctness, accuracy, and reliability of both digital mathematical libraries and computer algebra systems is a crucial attribute for modern research. In this paper, we present a novel approach to verify a digital mathematical library and two computer algebra systems with one another by converting mathematical expressions from one system to the other. We use our previously eveloped conversion tool (referred to as LaCASt) to translate formulae from the NIST Digital Library of Mathematical Functions to the computer algebra systems Maple and Mathematica. The contributions of our presented work are as follows: (1) we present the most comprehensive verification of computer algebra systems and digital mathematical libraries with one another; (2) we significantly enhance the performance of the underlying translator in terms of coverage and accuracy; and (3) we provide open access to translations for Maple and Mathematica of the formulae in the NIST Digital Library of Mathematical Functions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.09488v2-abstract-full').style.display = 'none'; document.getElementById('2201.09488v2-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 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> In: TACAS, Apr. 2022, pp. 87-105 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.11914">arXiv:2112.11914</a> <span> [<a href="https://arxiv.org/pdf/2112.11914">pdf</a>, <a href="https://arxiv.org/format/2112.11914">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</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> <p class="title is-5 mathjax"> Assisted Text Annotation Using Active Learning to Achieve High Quality with Little Effort </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Weeber%2C+F">Franziska Weeber</a>, <a href="/search/cs?searchtype=author&query=Hamborg%2C+F">Felix Hamborg</a>, <a href="/search/cs?searchtype=author&query=Donnay%2C+K">Karsten Donnay</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2112.11914v1-abstract-short" style="display: inline;"> Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality, annotated datasets with only a few manual annotations, thus strongly reducing annotation cost and effort. For this purpose, we combine an active learning (AL) ap… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.11914v1-abstract-full').style.display = 'inline'; document.getElementById('2112.11914v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.11914v1-abstract-full" style="display: none;"> Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality, annotated datasets with only a few manual annotations, thus strongly reducing annotation cost and effort. For this purpose, we combine an active learning (AL) approach with a pre-trained language model to semi-automatically identify annotation categories in the given text documents. To highlight our research direction's potential, we evaluate the approach on the task of identifying frames in news articles. Our preliminary results show that employing AL strongly reduces the number of annotations for correct classification of even these complex and subtle frames. On the framing dataset, the AL approach needs only 16.3\% of the annotations to reach the same performance as a model trained on the full dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.11914v1-abstract-full').style.display = 'none'; document.getElementById('2112.11914v1-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.08110">arXiv:2112.08110</a> <span> [<a href="https://arxiv.org/pdf/2112.08110">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> Academic Storage Cluster </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=von+Tottleben%2C+A">Alexander von Tottleben</a>, <a href="/search/cs?searchtype=author&query=Ihle%2C+C">Cornelius Ihle</a>, <a href="/search/cs?searchtype=author&query=Schubotz%2C+M">Moritz Schubotz</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2112.08110v1-abstract-short" style="display: inline;"> Decentralized storage is still rarely used in an academic and educational environment, although it offers better availability than conventional systems. It still happens that data is not available at a certain time due to heavy load or maintenance on university servers. A decentralized solution can help keep the data available and distribute the load among several peers. In our experiment, we crea… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.08110v1-abstract-full').style.display = 'inline'; document.getElementById('2112.08110v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.08110v1-abstract-full" style="display: none;"> Decentralized storage is still rarely used in an academic and educational environment, although it offers better availability than conventional systems. It still happens that data is not available at a certain time due to heavy load or maintenance on university servers. A decentralized solution can help keep the data available and distribute the load among several peers. In our experiment, we created a cluster of containers in Docker to evaluate a private IPFS cluster for an academic data store focusing on availability, GET/PUT performance, and storage needs. As sample data, we used PDF files to analyze the data transport in our peer-to-peer network with Wireshark. We found that a bandwidth of at least 100 kbit/s is required for IPFS to function but recommend at least 1000 kbit/s for smooth operation. Also, the hard disk and memory size should be adapted to the data. Other limiting factors such as CPU power and delay in the internet connection did not affect the operation of the IPFS cluster. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.08110v1-abstract-full').style.display = 'none'; document.getElementById('2112.08110v1-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 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">2 pages, 2 figures, Proceedings of the ACM/IEEE Joint Conference on Digital Libraries (JCDL), poster paper,</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.3.2; H.3.7; E.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.07421">arXiv:2112.07421</a> <span> [<a href="https://arxiv.org/pdf/2112.07421">pdf</a>, <a href="https://arxiv.org/format/2112.07421">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"> Towards A Reliable Ground-Truth For Biased Language Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Spinde%2C+T">Timo Spinde</a>, <a href="/search/cs?searchtype=author&query=Krieger%2C+D">David Krieger</a>, <a href="/search/cs?searchtype=author&query=Plank%2C+M">Manuel Plank</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2112.07421v2-abstract-short" style="display: inline;"> Reference texts such as encyclopedias and news articles can manifest biased language when objective reporting is substituted by subjective writing. Existing methods to detect bias mostly rely on annotated data to train machine learning models. However, low annotator agreement and comparability is a substantial drawback in available media bias corpora. To evaluate data collection options, we collec… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.07421v2-abstract-full').style.display = 'inline'; document.getElementById('2112.07421v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.07421v2-abstract-full" style="display: none;"> Reference texts such as encyclopedias and news articles can manifest biased language when objective reporting is substituted by subjective writing. Existing methods to detect bias mostly rely on annotated data to train machine learning models. However, low annotator agreement and comparability is a substantial drawback in available media bias corpora. To evaluate data collection options, we collect and compare labels obtained from two popular crowdsourcing platforms. Our results demonstrate the existing crowdsourcing approaches' lack of data quality, underlining the need for a trained expert framework to gather a more reliable dataset. By creating such a framework and gathering a first dataset, we are able to improve Krippendorff's $伪$ = 0.144 (crowdsourcing labels) to $伪$ = 0.419 (expert labels). We conclude that detailed annotator training increases data quality, improving the performance of existing bias detection systems. We will continue to extend our dataset in the future. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.07421v2-abstract-full').style.display = 'none'; document.getElementById('2112.07421v2-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> 17 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.07392">arXiv:2112.07392</a> <span> [<a href="https://arxiv.org/pdf/2112.07392">pdf</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"> Do You Think It's Biased? How To Ask For The Perception Of Media Bias </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Spinde%2C+T">Timo Spinde</a>, <a href="/search/cs?searchtype=author&query=Kreuter%2C+C">Christina Kreuter</a>, <a href="/search/cs?searchtype=author&query=Gaissmaier%2C+W">Wolfgang Gaissmaier</a>, <a href="/search/cs?searchtype=author&query=Hamborg%2C+F">Felix Hamborg</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</a>, <a href="/search/cs?searchtype=author&query=Giese%2C+H">Helge Giese</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="2112.07392v2-abstract-short" style="display: inline;"> Media coverage possesses a substantial effect on the public perception of events. The way media frames events can significantly alter the beliefs and perceptions of our society. Nevertheless, nearly all media outlets are known to report news in a biased way. While such bias can be introduced by altering the word choice or omitting information, the perception of bias also varies largely depending o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.07392v2-abstract-full').style.display = 'inline'; document.getElementById('2112.07392v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.07392v2-abstract-full" style="display: none;"> Media coverage possesses a substantial effect on the public perception of events. The way media frames events can significantly alter the beliefs and perceptions of our society. Nevertheless, nearly all media outlets are known to report news in a biased way. While such bias can be introduced by altering the word choice or omitting information, the perception of bias also varies largely depending on a reader's personal background. Therefore, media bias is a very complex construct to identify and analyze. Even though media bias has been the subject of many studies, previous assessment strategies are oversimplified, lack overlap and empirical evaluation. Thus, this study aims to develop a scale that can be used as a reliable standard to evaluate article bias. To name an example: Intending to measure bias in a news article, should we ask, "How biased is the article?" or should we instead ask, "How did the article treat the American president?". We conducted a literature search to find 824 relevant questions about text perception in previous research on the topic. In a multi-iterative process, we summarized and condensed these questions semantically to conclude a complete and representative set of possible question types about bias. The final set consisted of 25 questions with varying answering formats, 17 questions using semantic differentials, and six ratings of feelings. We tested each of the questions on 190 articles with overall 663 participants to identify how well the questions measure an article's perceived bias. Our results show that 21 final items are suitable and reliable for measuring the perception of media bias. We publish the final set of questions on http://bias-question-tree.gipplab.org/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.07392v2-abstract-full').style.display = 'none'; document.getElementById('2112.07392v2-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 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.07391">arXiv:2112.07391</a> <span> [<a href="https://arxiv.org/pdf/2112.07391">pdf</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"> TASSY -- A Text Annotation Survey System </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Spinde%2C+T">Timo Spinde</a>, <a href="/search/cs?searchtype=author&query=Sinha%2C+K">Kanishka Sinha</a>, <a href="/search/cs?searchtype=author&query=Meuschke%2C+N">Norman Meuschke</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2112.07391v2-abstract-short" style="display: inline;"> We present a free and open-source tool for creating web-based surveys that include text annotation tasks. Existing tools offer either text annotation or survey functionality but not both. Combining the two input types is particularly relevant for investigating a reader's perception of a text which also depends on the reader's background, such as age, gender, and education. Our tool caters primaril… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.07391v2-abstract-full').style.display = 'inline'; document.getElementById('2112.07391v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.07391v2-abstract-full" style="display: none;"> We present a free and open-source tool for creating web-based surveys that include text annotation tasks. Existing tools offer either text annotation or survey functionality but not both. Combining the two input types is particularly relevant for investigating a reader's perception of a text which also depends on the reader's background, such as age, gender, and education. Our tool caters primarily to the needs of researchers in the Library and Information Sciences, the Social Sciences, and the Humanities who apply Content Analysis to investigate, e.g., media bias, political communication, or fake news. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.07391v2-abstract-full').style.display = 'none'; document.getElementById('2112.07391v2-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 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.07384">arXiv:2112.07384</a> <span> [<a href="https://arxiv.org/pdf/2112.07384">pdf</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="Information Retrieval">cs.IR</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/10.1007/978-3-030-71305-8_17">10.1007/978-3-030-71305-8_17 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Identification of Biased Terms in News Articles by Comparison of Outlet-specific Word Embeddings </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Spinde%2C+T">Timo Spinde</a>, <a href="/search/cs?searchtype=author&query=Rudnitckaia%2C+L">Lada Rudnitckaia</a>, <a href="/search/cs?searchtype=author&query=Hamborg%2C+F">Felix Hamborg</a>, <a href="/search/cs?searchtype=author&query=Gipp%2C+B">Bela Gipp</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="2112.07384v1-abstract-short" style="display: inline;"> Slanted news coverage, also called media bias, can heavily influence how news consumers interpret and react to the news. To automatically identify biased language, we present an exploratory approach that compares the context of related words. We train two word embedding models, one on texts of left-wing, the other on right-wing news outlets. Our hypothesis is that a word's representations in both… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.07384v1-abstract-full').style.display = 'inline'; document.getElementById('2112.07384v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.07384v1-abstract-full" style="display: none;"> Slanted news coverage, also called media bias, can heavily influence how news consumers interpret and react to the news. To automatically identify biased language, we present an exploratory approach that compares the context of related words. We train two word embedding models, one on texts of left-wing, the other on right-wing news outlets. Our hypothesis is that a word's representations in both word embedding spaces are more similar for non-biased words than biased words. The underlying idea is that the context of biased words in different news outlets varies more strongly than the one of non-biased words, since the perception of a word as being biased differs depending on its context. While we do not find statistical significance to accept the hypothesis, the results show the effectiveness of the approach. For example, after a linear mapping of both word embeddings spaces, 31% of the words with the largest distances potentially induce bias. To improve the results, we find that the dataset needs to be significantly larger, and we derive further methodology as future research direction. To our knowledge, this paper presents the first in-depth look at the context of bias words measured by word embeddings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.07384v1-abstract-full').style.display = 'none'; document.getElementById('2112.07384v1-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 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </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=Gipp%2C+B&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Gipp%2C+B&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Gipp%2C+B&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