• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Sakaguchi Keisuke  坂口 慶祐

ORCIDConnect your ORCID iD *help
… Alternative Names

坂口 慶祐  サカグチ ケイスケ

Less
Researcher Number 20934087
Affiliation (Current) 2025: 東北大学, 情報科学研究科, 准教授
Affiliation (based on the past Project Information) *help 2025: 東北大学, 情報科学研究科, 准教授
2022 – 2023: 東北大学, 情報科学研究科, 准教授
Review Section/Research Field
Principal Investigator
Sections That Are Subject to Joint Review: Basic Section60030:Statistical science-related , Basic Section61030:Intelligent informatics-related / Basic Section 60030:Statistical science-related / Basic Section 61030:Intelligent informatics-related / Informatics
Keywords
Principal Investigator
記号処理 / 推論 / 深層学習 / マルチモーダル / 大規模言語モデル / 自然言語処理
  • Research Projects

    (2 results)
  • Research Products

    (30 results)
  •  マルチモーダル抽象推論過程の解明Principal Investigator

    • Principal Investigator
      坂口 慶祐
    • Project Period (FY)
      2025 – 2027
    • Research Category
      Grant-in-Aid for Scientific Research (B)
    • Review Section
      Basic Section 61030:Intelligent informatics-related
      Basic Section 60030:Statistical science-related
      Sections That Are Subject to Joint Review: Basic Section60030:Statistical science-related , Basic Section61030:Intelligent informatics-related
    • Research Institution
      Tohoku University
  •  現実世界の逐次的環境変化に協調的に適応するマルチモーダル自然言語理解モデルPrincipal Investigator

    • Principal Investigator
      坂口 慶祐
    • Project Period (FY)
      2021 – 2024
    • Research Category
      Fund for the Promotion of Joint International Research (Home-Returning Researcher Development Research)
    • Review Section
      Informatics
    • Research Institution
      Tohoku University

All 2024 2023 2022

All Journal Article Presentation

  • [Journal Article] ELQA: A Corpus of Metalinguistic Questions and Answers about English2023

    • Author(s)
      Shabnam Behzad, Keisuke Sakaguchi, Nathan Schneider, Amir Zeldes
    • Journal Title

      Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

      Volume: 0 Pages: 2031-2047

    • DOI

      10.18653/v1/2023.acl-long.113

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Journal Article] Empirical Investigation of Neural Symbolic Reasoning Strategies2023

    • Author(s)
      Yoichi Aoki, Keito Kudo, Tatsuki Kuribayashi, Ana Brassard, Masashi Yoshikawa, Keisuke Sakaguchi, Kentaro Inui
    • Journal Title

      Findings of the Association for Computational Linguistics: EACL 2023

      Volume: 0 Pages: 1154-1162

    • DOI

      10.18653/v1/2023.findings-eacl.86

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Journal Article] RealTime QA: What's the Answer Right Now?2023

    • Author(s)
      Jungo Kasai, Keisuke Sakaguchi, Yoichi Takahashi, Ronan Le Bras, Akari Asai, Xinyan Velocity Yu, Dragomir Radev, Noah A. Smith, Yejin Choi, Kentaro Inui
    • Journal Title

      Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track

      Volume: 0 Pages: 0-0

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Journal Article] Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning?2023

    • Author(s)
      Keito Kudo, Yoichi Aoki, Tatsuki Kuribayashi, Ana Brassard, Masashi Yoshikawa, Keisuke Sakaguchi, Kentaro Inui
    • Journal Title

      Proceedings of the 2023 Conference of the European Chapter of the Association for Computational Linguistics

      Volume: 0 Pages: 1343-1354

    • DOI

      10.18653/v1/2023.eacl-main.98

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-21K21343, KAKENHI-PROJECT-22H00524
  • [Journal Article] Test-time Augmentation for Factual Probing2023

    • Author(s)
      Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro Inui
    • Journal Title

      Findings of the Association for Computational Linguistics: EMNLP 2023

      Volume: 0 Pages: 3650-3661

    • DOI

      10.18653/v1/2023.findings-emnlp.236

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K21343, KAKENHI-PROJECT-21K17814
  • [Journal Article] I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation2023

    • Author(s)
      Chandra Bhagavatula, Jena D Hwang, Doug Downey, Ronan Le Bras, Ximing Lu, Keisuke Sakaguchi, Swabha Swayamdipta, Peter West, Yejin Choi
    • Journal Title

      Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

      Volume: 0 Pages: 9614-9630

    • DOI

      10.18653/v1/2023.acl-long.535

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] RLHFを用いた「面白い」短歌の自動生成の試み2024

    • Author(s)
      羽根田賢和, 浦川通, 田口雄哉, 田森秀明, 坂口慶祐
    • Organizer
      言語処理学会第30回年次大会論文集
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] 検出器の判断に基づく大規模言語モデルの生成テキストの特徴分析2024

    • Author(s)
      三浦東子, 谷口雅弥, 坂口慶祐, 乾健太郎
    • Organizer
      言語処理学会第30回年次大会論文集
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] 大規模言語モデルにおける日本語ゼロ照応解析能力の分析2024

    • Author(s)
      野末慎之介, 石月由紀子, 松林優一郎, 坂口慶祐
    • Organizer
      言語処理学会第30回年次大会論文集
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] 言語モデルからの知識削除:頻出実体の知識は副作用が破滅的2024

    • Author(s)
      高橋良允, 鴨田豪, BenjaminHeinzerling, 坂口慶祐, 乾健太郎
    • Organizer
      言語処理学会第30回年次大会論文集
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] J-UniMorph: 日本語の形態論における意味分類の体系化2024

    • Author(s)
      松崎孝介, 谷口雅弥, 乾健太郎, 坂口慶祐
    • Organizer
      言語処理学会第30回年次大会論文集
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] 自然画像で学習された画像埋め込みにダイアグラムを特徴づける情報は含まれているか?2024

    • Author(s)
      吉田遥音, 工藤慧音, 青木洋一, 田中涼太, 斉藤いつみ, 坂口慶祐, 乾健太郎
    • Organizer
      言語処理学会第30回年次大会論文集
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] 言語モデルの思考連鎖的推論における探索戦略の動的変化2024

    • Author(s)
      青木洋一, 工藤慧音, 曾根周作, 栗林樹生, 谷口雅弥, 坂口慶祐, 乾健太郎
    • Organizer
      言語処理学会第30回年次大会論文集
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] 日本の司法試験を題材としたGPTモデルの評価2024

    • Author(s)
      チェジョンミン, 笠井淳吾, 坂口慶祐
    • Organizer
      言語処理学会第30回年次大会論文集
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] 算術推論問題における自己回帰型言語モデルの内部機序2024

    • Author(s)
      工藤慧音, 青木洋一, 栗林樹生, 谷口雅弥, 曾根周作, 坂口慶祐, 乾健太郎
    • Organizer
      言語処理学会第30回年次大会論文集
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] 長文生成の多面的評価:人手評価と自動評価の向上を目指して2024

    • Author(s)
      鴨田豪, 浅井明里, BrassardAna, 坂口慶祐
    • Organizer
      言語処理学会第30回年次大会論文集
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] ニューラル記号推論における推論過程の教示方法2023

    • Author(s)
      青木洋一, 工藤慧音, Ana Brassard, 栗林樹生, 吉川将司, 坂口慶祐, 乾健太郎
    • Organizer
      言語処理学会第29回年次大会(NLP2023)
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] Empirical Investigation of Neural Symbolic Reasoning Strategies2023

    • Author(s)
      Yoichi Aoki, Keito Kudo, Tatsuki Kuribayashi, Ana Brassard, Masashi Yoshikawa, Keisuke Sakaguchi, and Kentaro Inui
    • Organizer
      Findings of the Association for Computational Linguistics: EACL 2023
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning?2023

    • Author(s)
      Keito Kudo, Yoichi Aoki, Tatsuki Kuribayashi, Ana Brassard, Masashi Yoshikawa, Keisuke Sakaguchi, and Kentaro Inui
    • Organizer
      Proceedings of the 2023 Conference of the European Chapter of the Association for Computational Linguistics
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] 因果的プロンプトによる NLI の敵対的ロバスト性の強化2023

    • Author(s)
      Pride Kavumba, Ana Brassard, Benjamin Heinzerling, 坂口慶祐, 乾健太郎
    • Organizer
      言語処理学会第29回年次大会(NLP2023)
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] 大規模言語モデルにおける暗黙の推論生成能力の評価2023

    • Author(s)
      根岸直生, 坂口慶祐, 乾健太郎
    • Organizer
      第22回情報科学技術フォーラム(FIT2023)
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] Hagi bot: LLMを用いた対話状態追跡と人間らしい振る舞いで自然な議論を行うマルチモーダル対話システム2023

    • Author(s)
      中野雄斗, 野末慎之介, 穀田一真, 有山知希, 佐藤魁, 曾根周作, 亀井遼平, 謝素春, 成田風香, 守屋彰二, 赤間怜奈, 松林優一郎, 坂口慶祐
    • Organizer
      人工知能学会研究会資料 言語・音声理解と対話処理研究会
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] Towards grammatically-informed feedback comments2023

    • Author(s)
      Diana Galvan-Sosa, Steven Coyne, 坂口慶祐, 乾健太郎
    • Organizer
      言語処理学会第29回年次大会(NLP2023)
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] Developing a Typology for Language Learning Feedback2023

    • Author(s)
      Steven Coyne, Diana Galvan-Sosa, 坂口慶祐, 乾健太郎
    • Organizer
      言語処理学会第29回年次大会(NLP2023)
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] テキストに基づくダイアグラム生成タスクの提案2023

    • Author(s)
      吉田遥音, 工藤慧音, 青木洋一, 坂口慶祐
    • Organizer
      NLP若手の会 第18回シンポジウム
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] 算術問題におけるニューラルモデルの構成的推論能力2023

    • Author(s)
      工藤慧音, 青木洋一, 栗林樹生, Ana Brassard, 吉川将司, 坂口慶祐, 乾健太郎
    • Organizer
      言語処理学会第29回年次大会(NLP2023)
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] Test-time Augmentation for Factual Probing2023

    • Author(s)
      Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro Inui
    • Organizer
      言語処理学会第29回年次大会(NLP2023)
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] 日本語学習のための形態意味中心の動詞活用2023

    • Author(s)
      松崎孝介, 谷口雅弥, 坂口慶祐, 乾健太郎
    • Organizer
      NLP若手の会 第18回シンポジウム
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] Large Language Models: What will happen next?2022

    • Author(s)
      Keisuke Sakaguchi
    • Organizer
      2022 BrainLink X-Lab Day, Korean Federation of Science and Technology Societies (KOFST)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K21343
  • [Presentation] Twist Decoding: Diverse Generators Guide Each Other2022

    • Author(s)
      Jungo Kasai, Keisuke Sakaguchi, Ronan Le Bras, Hao Peng, Ximing Lu, Dragomir Radev, Yejin Choi, Noah A. Smith
    • Organizer
      Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K21343

URL: 

Are you sure that you want to link your ORCID iD to your KAKEN Researcher profile?
* This action can be performed only by the researcher himself/herself who is listed on the KAKEN Researcher’s page. Are you sure that this KAKEN Researcher’s page is your page?

この研究者とORCID iDの連携を行いますか?
※ この処理は、研究者本人だけが実行できます。

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi