PageSourceSearch

https://keisuke-sakaguchi.github.io/news/

html keisuke-sakaguchi.github.io collected 2026-10-03 09:27:07 UTC 16,362 bytes, 21 lines download raw bytes

1<!DOCTYPE html> <html> <head> <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
vendor: 64 bytes, line 1
1 <script async src="https://www.googletagmanager.com/gtag/js?id=
1G-LSGEXQZ74W
vendor: 12 bytes, line 1
1"></script> 
1<script>
2  
vendor: 134 bytes, lines 2-6
2window.dataLayer = window.dataLayer || [];
3  function gtag(){dataLayer.push(arguments);}
4  gtag('js', new Date());
5
6  gtag('config', '
6G-LSGEXQZ74W
vendor: 4 bytes, line 6
6');
7</script>
7 <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no"> <meta http-equiv="X-UA-Compatible" content="IE=edge"> <title> Keisuke Sakaguchi | news </title> <meta name="description" content="Keisuke Sakaguchi, Associate Professor at Tohoku University. "> <link href="https://stackpath.bootstrapcdn.com/bootstrap/4.5.2/css/bootstrap.min.css" rel="stylesheet" integrity="sha512-MoRNloxbStBcD8z3M/2BmnT+rg4IsMxPkXaGh2zD6LGNNFE80W3onsAhRcMAMrSoyWL9xD7Ert0men7vR8LUZg==" crossorigin="anonymous"> <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/mdbootstrap/4.19.1/css/mdb.min.css" integrity="sha512-RO38pBRxYH3SoOprtPTD86JFOclM51/XTIdEPh5j8sj4tp8jmQIx26twG52UaLi//hQldfrh7e51WzP9wuP32Q==" crossorigin="anonymous"> <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.14.0/css/all.min.css" integrity="sha512-1PKOgIY59xJ8Co8+NE6FZ+LOAZKjy+KY8iq0G4B3CyeY6wYHN3yt9PW0XpSriVlkMXe40PTKnXrLnZ9+fkDaog==" crossorigin="anonymous"> <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/academicons/1.9.0/css/academicons.min.css" integrity="sha512-W4yqoT1+8NLkinBLBZko+dFB2ZbHsYLDdr50VElllRcNt2Q4/GSs6u71UHKxB7S6JEMCp5Ve4xjh3eGQl/HRvg==" crossorigin="anonymous"> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> <link href="https://fonts.googleapis.com/css2?family=Roboto:wght@300&amp;display=swap" rel="stylesheet"> <link rel="stylesheet" href="/assets/css/github.css"> <link rel="icon" href="data:image/svg+xml,&lt;svg%20xmlns=%22http://www.w3.org/2000/svg%22%20viewBox=%220%200%20100%20100%22&gt;&lt;text%20y=%22.9em%22%20font-size=%2290%22&gt;%F0%9F%92%A1&lt;/text&gt;&lt;/svg&gt;"> <link rel="stylesheet" href="/assets/css/main.css"> <link rel="canonical" href="/news/"> 
7<script async src="https://cdn.panelbear.com/analytics.js?site=D0uh9Msel0f"></script>
7 
7<script>
8    window.panelbear = window.panelbear || function() { (window.panelbear.q = window.panelbear.q || []).push(arguments); };
9    panelbear('config', { site: 'D0uh9Msel0f' });
10</script>
10 </head> <body class="fixed-top-nav "> <header> <nav id="navbar" class="navbar navbar-light navbar-expand-sm fixed-top"> <div class="container"> <button class="navbar-toggler collapsed ml-auto" type="button" data-toggle="collapse" data-target="#navbarNav" aria-controls="navbarNav" aria-expanded="false" aria-label="Toggle navigation"> <span class="sr-only">Toggle navigation</span> <span class="icon-bar top-bar"></span> <span class="icon-bar middle-bar"></span> <span class="icon-bar bottom-bar"></span> </button> <div class="collapse navbar-collapse text-right" id="navbarNav"> <ul class="navbar-nav ml-auto flex-nowrap"> <li class="nav-item "> <a class="nav-link" href="/"> about </a> </li> <li class="nav-item "> <a class="nav-link" href="/publications/"> publications </a> </li> <li class="nav-item "> <a class="nav-link" href="/cv/"> cv </a> </li> </ul> </div> </div> </nav> </header> <div class="container mt-5"> <div class="post"> <header class="post-header"> <h1 class="post-title">news</h1> <p class="post-description"></p> </header> <article> <div class="news"> <div class="table-responsive"> <table class="table table-sm table-borderless"> <tr> <th scope="row">2026/08/21             </th> <td> Three papers were accepted to <strong>EMNLP</strong>. </td> </tr> <tr> <th scope="row">2026/06/17             </th> <td> The paper on Unifying Accuracy and Efficiency for Robotics Evaluation has been accepted to <strong>IROS</strong>. </td> </tr> <tr> <th scope="row">2026/04/09             </th> <td> The paper on LLM’s Bar Exam Writing Task has been accepted to <strong>ICAIL</strong>. </td> </tr> <tr> <th scope="row">2026/04/01             </th> <td> I was promoted to Professor at Tohoku University. </td> </tr> <tr> <th scope="row">2026/01/04             </th> <td> The paper on LLM CoT faithfulness has been accepted to <strong>EACL</strong>. </td> </tr> <tr> <th scope="row">2025/10/27             </th> <td> The paper on LLM internal representations for Japanese (non-Gregorian) calendar has been accepted to <strong>AACL-IJCNLP</strong>. </td> </tr> <tr> <th scope="row">2025/09/19             </th> <td> The paper on side dffects of knowledge editing has been accepted to <strong>Blackbox NLP</strong>. </td> </tr> <tr> <th scope="row">2025/07/21             </th> <td> Our paper received a <strong>Best Paper Nomination at AIED 2025</strong>. </td> </tr> <tr> <th scope="row">2025/06/17             </th> <td> I gave a talk at the <strong>Earth Spieces Project (ESP)</strong>. </td> </tr> <tr> <th scope="row">2025/05/16             </th> <td> The paper on new rubric for evaluating explanations has been accepted to <strong>ACL</strong>. </td> </tr> <tr> <th scope="row">2025/04/03             </th> <td> The paper on Annotating Errors in Learners for Feedback has been accepted to <strong>AIED</strong>. </td> </tr> <tr> <th scope="row">2025/01/23             </th> <td> The paper on Sketch-to-diagram has been accepted to <strong>ICLR</strong>. </td> </tr> <tr> <th scope="row">2025/01/22             </th> <td> Two papers were accepted to <strong>NAACL</strong> on (1) consistency-driven rationale evaluation and (2) automated system input categorization scheme. </td> </tr> <tr> <th scope="row">2024/12/05             </th> <td> The paper on commonsense morality has been accepted to <strong>Nature Machine Intelligence</strong>. </td> </tr> <tr> <th scope="row">2024/09/20             </th> <td> The paper on Heuristics in Language Model Reasoning has been accepted to <strong>EMNLP</strong>. </td> </tr> <tr> <th scope="row">2024/07/10             </th> <td> The paper on explanation evaluation has been accepted to <strong>COLM</strong>. </td> </tr> <tr> <th scope="row">2024/02/19             </th> <td> The paper on beam search with patience has been accepted to <strong>LREC-COLING</strong>. </td> </tr> <tr> <th scope="row">2024/01/16             </th> <td> The paper on Procedural Knowledge Models for Language-based Planning and Re-Planning has been accepted to <strong>ICLR</strong>. </td> </tr> <tr> <th scope="row">2023/12/03             </th> <td> I gave a talk at BrainLink 2023, Korean Federation of Science and Technology Societies (KOFST), South Korea. </td> </tr> <tr> <th scope="row">2023/10/08             </th> <td> The paper on Test time augmentation has been accepted to <strong>Findings of EMNLP</strong> </td> </tr> <tr> <th scope="row">2023/09/22             </th> <td> The paper on Realtime QA has been accepted to <strong>NeurIPS</strong> Datasets and Benchmarks track. </td> </tr> <tr> <th scope="row">2023/08/23             </th> <td> “Empowering Local Open Source LLMs” has been accepted to <strong>NII Shonan Meeting</strong>. </td> </tr> <tr> <th scope="row">2023/08/07             </th> <td> I gave a talk at CWRU-TOHOKU Joint Workshop. </td> </tr> <tr> <th scope="row">2023/05/27             </th> <td> Two papers were accepted to <strong>ACL</strong> on (1) Corpus of Metalinguistic Questions and Answers and (2) Inductive Knowledge Distillation. </td> </tr> <tr> <th scope="row">2023/04/05             </th> <td> I gave an online lecture at Sungkyunkwan University, South Korea. </td> </tr> <tr> <th scope="row">2023/01/23             </th> <td> I gave a talk at AIST AI Research Center, Japan. </td> </tr> <tr> <th scope="row">2023/01/21             </th> <td> Two papers were accepted to <strong>EACL</strong> on (1) Neural Symbolic Reasoning Strategies and (2) Compositionality in Arithmetic Reasoning. </td> </tr> <tr> <th scope="row">2022/11/20             </th> <td> Our paper received <strong>AACL SRW 2022 Best Paper Award</strong>
10 <img class="emoji" title=":trophy:" alt=":trophy:" src="https://github.githubassets.com/images/icons/emoji/unicode/1f3c6.png" height="20" width="20"> </td> </tr> <tr> <th scope="row">2022/10/25             </th> <td> I gave a talk at BrainLink 2022, Korean Federation of Science and Technology Societies (KOFST), South Korea. </td> </tr> <tr> <th scope="row">2022/10/06             </th> <td> A paper was accepted to <strong>EMNLP</strong> on Twist Decoding. </td> </tr> <tr> <th scope="row">2022/09/27             </th> <td> I gave a talk at Knowledge and Information Research Team, AIST AI Research Center, Japan. </td> </tr> <tr> <th scope="row">2022/08/23             </th> <td> I gave a talk at University of Tokyo. </td> </tr> <tr> <th scope="row">2022/07/01             </th> <td> I joined at Tohoku University NLP lab, Japan.🎋 </td> </tr> <tr> <th scope="row">2022/04/07             </th> <td> Two papers were accepted to <strong>NAACL</strong> on (1) Bidimensional Leaderboards and (2) Transparent Human Evaluation for Image Captioning. </td> </tr> <tr> <th scope="row">2021/12/08             </th> <td> A paper was accepted to <strong>AAAI’22-Workshop on Interactive Machine Learning</strong> on Interactive Learning of Scripts. </td> </tr> <tr> <th scope="row">2021/09/17             </th> <td> A paper was accepted to <strong>Findings of EMNLP</strong> on Partially Ordered Scripts Generation. </td> </tr> <tr> <th scope="row">2021/09/01             </th> <td> Our paper is published in <strong>Communications of the ACM</strong>. </td> </tr> <tr> <th scope="row">2020/12/02             </th> <td> A paper was accepted to <strong>AAAI</strong> on Symbolic and Neural Commonsense Knowledge Graphs. </td> </tr> <tr> <th scope="row">2020/09/15             </th> <td> A paper was accepted to <strong>EMNLP</strong> on Open Domain Procedural Text. </td> </tr> <tr> <th scope="row">2020/04/03             </th> <td> A paper was accepted to <strong>ACL</strong> on Uncertain Natural Language Inference. </td> </tr> <tr> <th scope="row">2020/02/11             </th> <td> Our paper, WinoGrande, received <strong>AAAI 2020 Outstanding Paper Award</strong> <img class="emoji" title=":trophy:" alt=":trophy:" src="https://github.githubassets.com/images/icons/emoji/unicode/1f3c6.png" height="20" width="20"> </td> </tr> <tr> <th scope="row">2020/02/10             </th> <td> A paper was accepted to <strong>LREC</strong> on Universal Decompositional Semantics Dataset and Toolkit. </td> </tr> <tr> <th scope="row">2019/12/19             </th> <td> A paper was accepted to <strong>ICLR</strong> on Abductive Commonsense Reasoning. </td> </tr> <tr> <th scope="row">2019/11/10             </th> <td> A paper was accepted to <strong>AAAI</strong> on WinoGrande: An Adversarial Winograd Schema Challenge at Scale. </td> </tr> <tr> <th scope="row">2019/08/13             </th> <td> A paper was accepted to <strong>EMNLP</strong> on WIQA: A dataset for “What if…” reasoning over procedural text. </td> </tr> <tr> <th scope="row">2019/04/27             </th> <td> I successfully defended my thesis. </td> </tr> <tr> <th scope="row">2019/04/20             </th> <td> A paper was accepted to <strong>ACL</strong> on Efficient Annotation of Scalar Labels (EASL). </td> </tr> <tr> <th scope="row">2018/08/20             </th> <td> I joined Allen Institute for Artificial Intelligence (AI2).💡 </td> </tr> <tr> <th scope="row">2018/03/30             </th> <td> I gave a talk at Allen Institute for Artificial Intelligence (AI2). </td> </tr> <tr> <th scope="row">2018/02/22             </th> <td> I gave a video talk at Grammarly Research. </td> </tr> <tr> <th scope="row">2018/02/09             </th> <td>
10 I gave a talk at Amazon Research. </td> </tr> <tr> <th scope="row">2017/12/14             </th> <td> I gave a talk at Chiba Institute of Technology (Japan). </td> </tr> <tr> <th scope="row">2017/12/12             </th> <td> I gave a talk at NTT Communication Science Laboratories (Japan). </td> </tr> <tr> <th scope="row">2017/12/08             </th> <td> I gave a talk at Tohoku University (Japan). </td> </tr> <tr> <th scope="row">2017/12/05             </th> <td> I gave a talk at Tokyo Metropolitan University (Japan). </td> </tr> <tr> <th scope="row">2017/10/18             </th> <td> I gave a presentation at Amazon Graduate Research Symposium. </td> </tr> <tr> <th scope="row">2017/09/01             </th> <td> A paper was accepted to <strong>IJCNLP</strong> on Grammatical Error Correction with Neural Reinforcement Learning. </td> </tr> <tr> <th scope="row">2017/07/01             </th> <td> A paper was accepted to <strong>BEA</strong> on Grammatical Error Correction into the Future. </td> </tr> <tr> <th scope="row">2017/06/04             </th> <td> Our paper on error-repair dependency parsing received <strong>ACL 2017 Outstanding Paper Award</strong> <img class="emoji" title=":trophy:" alt=":trophy:" src="https://github.githubassets.com/images/icons/emoji/unicode/1f3c6.png" height="20" width="20"> </td> </tr> <tr> <th scope="row">2017/05/22             </th> <td> I started a research internship at IBM T. J. Watson Research Center (DeepQA). </td> </tr> <tr> <th scope="row">2017/03/31             </th> <td> A paper was accepted to <strong>ACL</strong> on Error-repair Dependency Parsing for Ungrammatical Texts. </td> </tr> <tr> <th scope="row">2016/11/12             </th> <td> A paper was accepted to <strong>AAAI</strong> on Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network. </td> </tr> <tr> <th scope="row">2016/07/29             </th> <td> A paper was accepted to <strong>EMNLP</strong> on Reference-less Evaluation Metrics in Grammatical Error Correction. </td> </tr> <tr> <th scope="row">2016/07/29             </th> <td> A paper was accepted to <strong>EMNLP</strong> on Universal Decompositional Semantics. </td> </tr> <tr> <th scope="row">2016/05/24             </th> <td> A paper was accepted to <strong>ACL</strong> on Phrase Structure Annotation and Parsing for Learner English. </td> </tr> <tr> <th scope="row">2016/04/05             </th> <td> A paper was accepted to <strong>TACL</strong> on Reassessing the Goals of Grammatical Error Correction. </td> </tr> </table> </div> </div> </article> </div> </div> </body> 
10<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.5.1/jquery.min.js" integrity="sha512-bLT0Qm9VnAYZDflyKcBaQ2gg0hSYNQrJ8RilYldYQ1FxQYoCLtUjuuRuZo+fjqhx/qtq/1itJ0C2ejDxltZVFg==" crossorigin="anonymous"></script>
10 
10<script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/2.4.4/umd/popper.min.js" integrity="sha512-eUQ9hGdLjBjY3F41CScH3UX+4JDSI9zXeroz7hJ+RteoCaY+GP/LDoM8AO+Pt+DRFw3nXqsjh9Zsts8hnYv8/A==" crossorigin="anonymous"></script>
10 
10<script src="https://stackpath.bootstrapcdn.com/bootstrap/4.5.2/js/bootstrap.min.js" integrity="sha512-M5KW3ztuIICmVIhjSqXe01oV2bpe248gOxqmlcYrEzAvws7Pw3z6BK0iGbrwvdrUQUhi3eXgtxp5I8PDo9YfjQ==" crossorigin="anonymous"></script>
10 
10<script src="https://cdnjs.cloudflare.com/ajax/libs/mdbootstrap/4.19.1/js/mdb.min.js" integrity="sha512-Mug9KHKmroQFMLm93zGrjhibM2z2Obg9l6qFG2qKjXEXkMp/VDkI4uju9m4QKPjWSwQ6O2qzZEnJDEeCw0Blcw==" crossorigin="anonymous"></script>
10 
10<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/medium-zoom.min.js" integrity="sha256-EdPgYcPk/IIrw7FYeuJQexva49pVRZNmt3LculEr7zM=" crossorigin="anonymous"></script>
10 
10<script src="/assets/js/zoom.js"></script>
10 
10<script src="/assets/js/common.js"></script>
10 
10<script type="text/javascript"> 
11        function play(audio_id){
12            var audio = document.getElementById(audio_id);
13            audio.play();
14        }
15</script>
15 
15<script type="text/javascript">
16  window.MathJax = {
17    tex: {
18      tags: 'ams'
19    }
20  };
21</script>
21 
21<script defer type="text/javascript" id="MathJax-script" src="https://cdn.jsdelivr.net/npm/[email protected]/es5/tex-mml-chtml.js"></script>
21 </html>

Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.