峯島 宏次

• 慶應義塾大学 文学部 哲学専攻 准教授
• 研究紹介

連絡先

• 〒108-8345 東京都港区三田2-15-45 慶應義塾大学文学部
• E-mail: minesima [at] abelard.flet.keio.ac.jp

授業

• 2024年度の講義
授業の情報を随時更新しています。

研究プロジェクト

• JST CREST 自然言語の非線形性の計算論モデル

お知らせ

• 大学院入試（修士課程・博士課程）

Upcoming talks/events

• Logic Seminar: Prof. Giovanni Sambin, "From Constructive Topology to Dynamics in Foundations, and Back" , Keio University, September 10, 2024.
• The 14th International Conference on the Theory and Application of Diagrams (Diagrams 2024), Münster, Germany, September 27 - October 1, 2024.
• The 3rd International Conference on Human and Artificial Rationalities (HAR 2024), Paris, France, September 17-20, 2024.

Recent talks/events

• The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), Bangkok, Thailand, August 11-16, 2024.
• CogSci 2024: Annual Meeting of the Cognitive Science Society, Rotterdam, the Netherlands, July 24-27, 2024.
• 峯島宏次「人間とAIによる論理推論」 未来共生デザインセンターキックオフシンポジウム, 慶應義塾大学, 2024年7月18日.
• The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Torino, Italy, May 20-25, 2024.
• Two lectures and discussion by Prof. Mark van Atten on various issues in Brouwer and Husserl's logic, Keio University, April 16, 2024.
• Koji Mineshima, Expressing Disagreement and Concession, French-Japanese Colloquium, Disagreement in Logic and Reasoning, IHPST, Paris, France, March 25-26, 2024.
• Koji Mineshima, Is Reasoning Without Logic Viable? An Evaluation of Large Language Models using the NeuBAROCO dataset, Seminar at IHPST and Université Paris 1, Paris, France, March 22, 2024.
• France-Japan Workshop on "Disagreement in Logic and Reasoning" and a Special Session on "A Humanity and Social Science Approach to Cybersecurity Research: An EU Horizon 2020 Project", Keio University, March 2, 2024.
• Workshop with Jocelyn Benoist: Discussions on Wittgenstein and Beyond, Keio University, February 29, 2024.
• 6th Asian Workshop on Philosophical Logic (AWPL2024), Hokkaido University, March 4-6, 2024.
• 言語処理学会第30回年次大会 (NLP2024), 神戸国際会議場, 2024年3月11日-15日.
• UNESCO世界論理デー記念パネルセッション「これからの論理（学）教育」オンライン, 2024年1月14日, 14:30−17:00.
• Hayate Funakura and Koji Mineshima, Computational Semantics and Evaluation Benchmark for Interrogative Sentences via Combinatory Categorial Grammar, Pacific Asia Conference on Language, Information and Computation (PACLIC 37), Hong Kong, December 2–5, 2023.
• 峯島宏次「言葉の意味をどのように説明するか―形式意味論と分布意味論を比較する観点から―」日本語文法学会第24回大会, シンポジウム「意味論研究の新地平」, 関西大学, 2023年12月3日.
• Logic and Engineering of Natural Language Semantics 20 (LENLS20), Hybrid (Osaka University Nakanoshima Center | Online), November 18-20, 2023.
• Yuri Sato and Koji Mineshima, "Can machines and humans use negation when describing images?", 2nd International Conference on Human and Artificial Rationalities, Hybrid (Paris, France), September 19-22, 2023.
• 国際哲学人文学会議(CIPSH)国際学会 (CIPSH International Conference), Humanities in the Global and Digital Age: The Role of Humanities Research Traditions and Interactions in Contemporary Society, 東京大学本郷キャンパス（8月23日）, 慶應義塾大学三田キャンパス（8月24日）, 2023年.
• Hitomi Yanaka and Koji Mineshima, "Compositional Evaluation on Japanese Textual Entailment and Similarity", Presentation of a paper accepted by TACL, The 61st Annual Meeting of the Association for Computational Linguistics (ACL2023), Toronto, Canada, July 12, 2023.
• Yuji Nishiyama and Koji Mineshima, "Concealed Questions and Free Enrichment", The 18th International Pragmatics Conference (IPrA 2023), Brussels, Belgium, July 13, 2023.
• 慶應義塾大学文学部公開講座「越境する文学部」 「本と文字は時空を超える」慶應義塾大学三田キャンパス, 2023年7月1日.
• Risako Ando, Takanobu Morishita, Hirohiko Abe, Koji Mineshima, Mitsuhiro Okada, "Evaluating Large Language Models with NeuBAROCO: Syllogistic Reasoning Ability and Human-like Biases", Natural Logic Meets Machine Learning IV, Workshop at IWCS2023, Nancy, France, June 20, 2023.
• Gaëtan Margueritte, Koji Mineshima, Daisuke Bekki, "Multi-purpose neural network for French categorial grammars", The 15th International Conference on Computational Semantics (IWCS 2023), Nancy, France, June 20-23, 2023.
• 峯島宏次, 窪⽥悠介, 宮尾祐介, 窪⽥愛, 船蔵颯「多⾔語に対応した汎⽤的な構成的意味論の計算フレームワークの構築」 日本言語学会第166回大会, 専修大学, 2023年6月17日-18日.
• Past Events

Software/language resources

• ccg2lambda: An open-source CCG-based semantic parser and inference system for English and Japanese. [使い方] [ccg2lambdaによる含意関係認識]
• ABC Treebank: An open-source categorial grammar treebank for Japanese

出版物 [researchmap] [Google Scholar] [DBLP] [ACL Anthology] [Semantic Scholar]

2024年

• Hirohiko Abe, Risako Ando, Takanobu Morishita, Kentaro Ozeki, Koji Mineshima, and Mitsuhiro Okada, Abductive Reasoning with Syllogistic Forms in Large Language Models. To apearar in Proceedings of the 3rd International Conference on Human and Artificial Rationalities (HAR 2024), Lecture Notes in Computer Science (LNCS).

• Kentaro Ozeki, Risako Ando, Takanobu Morishita, Hirohiko Abe, Koji Mineshima, and Mitsuhiro Okada, Exploring Reasoning Biases in Large Language Models Through Syllogism: Insights from the NeuBAROCO Dataset. Findings of the Association for Computational Linguistics ACL 2024, 16063-16077. [Paper] [arXiv] [Data]

• Yuri Sato, Ayaka Suzuki, and Koji Mineshima, Capturing stage-level and individual-level information from photographs: Human-AI comparison. Proceedings of the 46th Annual Conference of the Cognitive Science Society (CogSci2024), 803-810, 2024. [Paper]

• Yuri Sato, Ayaka Suzuki and Koji Mineshima, Building a large dataset of human-generated captions for science diagrams. Diagrammatic Representation and Inference: Proceedings of 14th International Conference on the Theory and Application of Diagrams (Diagrams 2024), Lecture Notes in Computer Science (LNAI 14981), Springer, 393-401, 2024. [Paper]

• Risako Ando, Kentaro Ozeki, Takanobu Morishita, Hirohiko Abe, Koji Mineshima, and Mitsuhiro Okada, Can Euler Diagrams Improve Syllogistic Reasoning in Large Language Models?, Diagrammatic Representation and Inference: Proceedings of 14th International Conference on the Theory and Application of Diagrams (Diagrams 2024), Lecture Notes in Computer Science (LNAI 14981), Springer, 232-248, 2024. [Paper] [Data]

• Ai Kubota, Takuma Sato, Takayuki Amamoto, Ryota Akiyoshi, and Koji Mineshima, Annotation of Japanese Discourse Relations Focusing on Concessive Inferences. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 1215–1224, 2024. [Paper] [Data]

• Yuri Sato and Koji Mineshima, Can Machines and Humans Use Negation When Describing Images? Human and Artificial Rationalities (HAR 2023). Lecture Notes in Computer Science (LNCS) 14522, 39-47, Springer, 2024. [Link]

• Yukiko Yana, Koji Mineshima and Daisuke Bekki, A Proof-Theoretic Approach to the Binding Problem. Proceedings of 6th Asian Workshop on Philosophical Logic (AWPL2024), 129-139, 2024

• 谷中瞳, 峯島宏次 「AIは言語の基盤を獲得するか：推論の体系性の観点から」 『認知科学』31巻1号, 27-45, 2024年. [Paper]

• 森下貴允, 安東里沙子, 阿部裕彦, 小関健太郎, 峯島宏次, 岡田光弘 「NeuBAROCO データセットによる大規模言語モデルの推論能力の検証」 言語処理学会第30回年次大会発表論文集, 2024年. [Paper]

• 佐藤拓真, 窪田愛, 峯島宏次 「BERTはどのように逆接の談話関係を判定しているか─Attentionと品詞を手がかりとして─」 言語処理学会第30回年次大会発表論文集, 2024年. [Paper]

• 船蔵颯, 櫻川貴司, 峯島宏次 「節埋め込みの意味論に動機づけられたプロービング」 言語処理学会第30回年次大会発表論文集, 2024年. [Paper]

2023年

• Hayate Funakura and Koji Mineshima, Computational Semantics and Evaluation Benchmark for Interrogative Sentences via Combinatory Categorial Grammar. Proceedings of Pacific Asia Conference on Language, Information and Computation (PACLIC 37), 764-774, 2023. [Paper] [arXiv]

• Risako Ando, Takanobu Morishita, Hirohiko Abe, Koji Mineshima, and Mitsuhiro Okada, Evaluating Large Language Models with NeuBAROCO: Syllogistic Reasoning Ability and Human-like Biases. Proceedings of the 4th Natural Logic Meets Machine Learning (NALOMA) Workshop, 1-11, 2023. [Paper] [arXiv] [Data]

• Gaëtan Margueritte, Koji Mineshima, and Daisuke Bekki, Multi-purpose neural network for French categorial grammars. Proceedings of the 15th International Conference on Computational Semantics (IWCS 2023), 78-82, 2023. [Paper]

• Yuri Sato, Koji Mineshima, and Kazuhiro Ueda. Can Negation Be Depicted? Comparing Human and Machine Understanding of Visual Representations. Cognitive Science, Volume 47, Issue 3, e13258, 2023. [Paper]

• 田中久美子, 峯島宏次「言語と計算―構造と構成の再構築に向けて」 『現代思想』2023年7月号, 140-151頁. [Link]

• 峯島宏次, 窪⽥悠介, 宮尾祐介, 窪⽥愛, 船蔵颯「多⾔語に対応した汎⽤的な構成的意味論の計算フレームワークの構築」 日本言語学会第166回大会, 専修大学, 2023年. [予稿集]

• 小谷野華那, 谷中瞳, 峯島宏次, 戸次大介 「日本語数量表現コーパスと推論データセットの構築」 自然言語処理, 30巻2号, 432-455頁, 2023年. [Link]

• 窪田愛, 佐藤拓真, 天本貴之, 秋吉亮太, 峯島宏次 「逆接の推論関係に着目した日本語談話関係アノテーション」 言語処理学会第29回年次大会発表論文集, 2023年. 委員特別賞. [Paper]

• 佐藤拓真, 窪田愛, 峯島宏次 「含意関係と感情極性は対立的談話関係を捉えられるか」 言語処理学会第29回年次大会発表論文集, 2023年. [Paper]

• 窪田悠介, 林則序, 天本貴之, 峯島宏次 「比較文の意味解析のための「深い」係り受け関係の解析」 言語処理学会第29回年次大会発表論文集, 2023年. [Paper]

• 小谷野華那, 谷中瞳, 峯島宏次, 戸次大介 「汎用言語モデルは日本語の助数辞を理解しているか」 言語処理学会第29回年次大会発表論文集, 2023年. [Paper]

2022年

• Izumi Haruta, Koji Mineshima, and Daisuke Bekki. Implementing Natural Language Inference for Comparatives. Journal of Language Modelling, Vol.10, No.1, 139-191, 2022. [Paper]

• Hitomi Yanaka and Koji Mineshima. Compositional Evaluation on Japanese Textual Entailment and Similarity. Transactions of the Association for Computational Linguistics (TACL) 10: 1266–1284, 2022. [Paper] [arXiv] [Data]

• Yuri Sato and Koji Mineshima. Visually Analyzing Universal Quantifiers in Photograph Captions. Proceedings of the 13th International Conference on the Theory and Application of Diagrams (Diagrams2022), Lecture Notes in Artificial Intelligence (LNAI) 13462, 373–377, 2022. [Link]

• Kana Koyano, Hitomi Yanaka, Koji Mineshima, and Daisuke Bekki. Annotating Japanese Numeral Expressions for a Logical and Pragmatic Inference Dataset. Proceedings of the 18th Joint ACL-ISO Workshop on Interoperable Semantic Annotation (ISA-18), 127-132, 2022. [Paper]

• 小谷野華那, 谷中瞳, 峯島宏次, 福田浩司, 橋爪宏典, 戸次大介 「供述調書に現れる数量表現の推論テストセットの構築」 言語処理学会第28回年次大会発表論文集, 2022年.

2021年

• Yukiko Yana, Koji Mineshima, and Daisuke Bekki. The Proviso Problem from a Proof-Theoretic Perspective. Proceedings of Logical Aspects of Computational Linguistics 2021 (LACL2021), 159-176, 2021.

• Atsushi Sumita, Koji Mineshima, and Yusuke Miyao. Talking with the Theorem Prover to Interactively Solve Natural Language Inference. Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation (PACLIC35), 415-424, 2021. [Paper]

• Hitomi Yanaka and Koji Mineshima. Assessing the Generalization Capacity of Pre-trained Language Models through Japanese Adversarial Natural Language Inference. Proceedings of BlackboxNLP 2021: Analyzing and interpreting neural networks for NLP, Workshop at EMNLP2021, 337-349, 2021. [Paper] [Code]

• Yuri Sato and Koji Mineshima. Can Humans and Machines Classify Photographs as Depicting Negation? Diagrammatic Representation and Inference (Diagrams 2021), Lecture Notes in Computer Science, Volume 12909, 348-352, 2021. [Link]

• Hitomi Yanaka, Koji Mineshima, and Kentaro Inui. SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 103-119, 2021. [Paper] [arXiv] [Code]

• Yuri Sato, Koji Mineshima, and Kazuhiro Ueda. Visual Representation of Negation: Real World Data Analysis on Comic Image Design. Proceedings of the 43rd Annual Conference of the Cognitive Science Society (CogSci2021), 1166-1172, 2021. [Paper] [arXiv]

• Riko Suzuki, Hitomi Yanaka, Koji Mineshima, and Daisuke Bekki. Building a Video-and-Language Dataset with Human Actions for Multimodal Logical Inference. Proceedings of the 1st Workshop on Multimodal Semantic Representations (MMSR), 102-107, 2021. [Paper]

• Hitomi Yanaka, Koji Mineshima, and Kentaro Inui. Exploring Transitivity in Neural NLI Models through Veridicality. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL2021), 920-934, 2021. [Paper] [arXiv] [Code]

• 谷中瞳, 峯島宏次「JSICK：日本語構成的推論・類似度データセットの構築」人工知能学会第35回全国大会, 2021年. [Paper]

• 横関茉衣, 村上夏輝, 鈴木莉子, 谷中瞳, 峯島宏次, 戸次大介「マルチモーダル推論のための動画アクションデータセットの構築」人工知能学会第35回全国大会, 2021年. [Paper]

• 峯島宏次「書評 飯田隆『日本語と論理―哲学者、その謎に挑む』」『科学哲学』第53巻, 第2号, 321-323, 2021年. [Link]

• 佐藤有理, 峯島宏次「論理の図形表現」『認知科学』第28巻, 第1号, 139-152, 2021年. [Paper]

• 窪田悠介, 峯島宏次, 林則序, 岡野伸哉 「ABCツリーバンク：学際的な言語研究のための基盤資源」 言語処理学会第27回年次大会発表論文集, 2021年. [Paper]

• 隅田敦, 峯島宏次, 宮尾祐介 「定理証明に基づく対話的な自然言語推論システム」 言語処理学会第27回年次大会発表論文集, 2021年. [Paper]

• 谷中瞳, 峯島宏次, 乾健太郎 「ニューラルネットが学習する意味表現は体系性を持つか」 言語処理学会第27回年次大会発表論文集, 2021年. [Paper]

2020年

• Izumi Haruta, Koji Mineshima, and Daisuke Bekki. Combining Event Semantics and Degree Semantics for Natural Language Inference. Proceedings of the 28th International Conference on Computational Linguistics (Coling2020), 1758–1764, 2020. [Paper] [arXiv] [Code]

• Yuri Sato and Koji Mineshima. Depicting Negative Information in Photographs, Videos, and Comics: A Preliminary Analysis. Diagrammatic Representation and Inference (Diagrams 2020), Lecture Notes in Computer Science, Volume 12169, 485-489, 2020. [Link]

• Izumi Haruta, Koji Mineshima, and Daisuke Bekki. Logical Inferences with Comparatives and Generalized Quantifiers. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop (ACL-SRW2020), 263-270, 2020. [Paper] [arXiv] [Code]

• Hitomi Yanaka, Koji Mineshima, Daisuke Bekki, and Kentaro Inui. Do Neural Models Learn Systematicity of Monotonicity Inference in Natural Language? Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL2020), 6105-6117, 2020. [Paper] [arXiv] [Code]

• Yusuke Kubota, Koji Mineshima, Noritsugu Hayashi, Shinya Okano. Development of a General-Purpose Categorial Grammar Treebank. Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), 5195-5201, 2020. [Paper]

• 峯島宏次「人工知能と言語」『神奈川大学評論』95号, 特集「AIとシンギュラリティ ー 知識基盤社会の行方」, 64-71, 2020年. [出版社のページ] [Penultimate Draft]

• 峯島宏次「論理と文法」『数学セミナー』701号, 特集「言語の数理」, 30-35, 2020年. [出版社のページ]

• 春田和泉, 峯島宏次, 戸次大介 「CCGと自動定理証明による比較表現の計算意味論」 人工知能学会第34回全国大会, 2020年. [Paper]

• 谷中瞳, 峯島宏次, 戸次大介, 乾 健太郎 「ニューラルネットワークによる自然言語推論の可能性」 人工知能学会第34回全国大会, 2020年. 全国大会優秀賞. [Paper]

• 大西舞子, 谷中瞳, 峯島宏次, 戸次大介 「CCGと定理証明器による自然言語の時間関係認識」 人工知能学会第34回全国大会, 2020年. [Paper]

• 谷中瞳, 峯島宏次, 戸次大介, 乾健太郎 「ニューラルネットは自然言語推論の体系性を学習するか」, 言語処理学会第26回年次大会発表論文集, C3-1, 2020年. [Paper]

• 飯野早貴, 石田真捺, 小谷野華那, 松本留奈, 鈴木莉子, 谷中瞳, 峯島宏次, 戸次大介 「マルチモーダル推論評価のための日本語データセットの試案」, 言語処理学会第26回年次大会発表論文集, P4-13, 2020年. [Paper]

• 谷中瞳, 峯島宏次, 山田彬尭, 山口悠, 窪田悠介, Lasha Abzianidze, Johan Bos 「多言語統語・意味情報コーパス Parallel Meaning Bank 日本語版の構築」 言語処理学会第26回年次大会発表論文集, F5-2, 2020年. [Paper] [Slides]

• 伊藤美賀, 佐藤七海, 田上青空, 谷中瞳, 峯島宏次, 戸次大介 「汎用言語モデルBERTを用いた多言語テキストにおける意味現象タグ予測」 言語処理学会第26回年次大会発表論文集, P5-5, 2020年. [Paper]

• 秋山雛乃, 石嶋美咲, 石田真捺, 高野紗輝, 鈴木莉子, 谷中瞳, 峯島宏次, 戸次大介 「CCGとCoqを用いた日本語マルチモーダル推論システムの構築」 言語処理学会第26回年次大会発表論文集, P6-13, 2020年. [Paper]

2019年

• Izumi Haruta, Koji Mineshima and Daisuke Bekki. A CCG-based Compositional Semantics and Inference System for Comparatives. Proceedings of the 33rd Pacific Asia Conference on Language, Information and Computation (PACLIC 33), 47-56, 2019. [Paper] [arXiv] [Code]

• Masashi Yoshikawa, Hiroshi Noji, Koji Mineshima and Daisuke Bekki. Automatic Generation of High Quality CCGbanks for Parser Domain Adaptation. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL2019), 129-139, 2019. [Paper] [arXiv] [Code]

• Hitomi Yanaka, Koji Mineshima, Daisuke Bekki, Kentaro Inui, Satoshi Sekine, Lasha Abzianidze and Johan Bos. Can Neural Networks Understand Monotonicity Reasoning? Proceedings of BlackboxNLP 2019: Analyzing and interpreting neural networks for NLP, Workshop at ACL2019, 31–40, 2019. [Paper] [arXiv] [Code]

• Riko Suzuki, Hitomi Yanaka, Masashi Yoshikawa, Koji Mineshima and Daisuke Bekki. Multimodal Logical Inference System for Visual-Textual Entailment. Proceedings of the 2019 ACL Student Research Workshop (ACL-SRW), 386–392, 2019. [Paper] [arXiv] [Code]

• Hitomi Yanaka, Koji Mineshima, Daisuke Bekki, Kentaro Inui, Satoshi Sekine, Lasha Abzianidze and Johan Bos. HELP: A Dataset for Identifying Shortcomings of Neural Models in Monotonicity Reasoning. Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), Workshop at NAACL-HLT2019, 250–255, 2019. [Paper] [arXiv] [Code]

• Riko Suzuki, Hitomi Yanaka, Masashi Yoshikawa, Koji Mineshima and Daisuke Bekki. Towards building a logical inference system for image retrieval. (Extended abstract), Workshop on Shortcomings in Vision and Language (SiVL), Workshop at NAACL-HLT2019.

• Yusuke Kubota, Koji Mineshima, Robert Levine and Daisuke Bekki. Underspecification and interpretive parallelism in Dependent Type Semantics. Proceedings of Computing Semantics with Types, Frames and Related Structures (CSTFRS), IWCS 2019 Workshop, 1-9, 2019. [Paper]

• Kazuki Watanabe, Koji Mineshima and Daisuke Bekki. Questions in Dependent Type Semantics. Proceedings of the Sixth Natural Language and Computer Science 6 (NLCS 2019), Workshop at the 13th International Conference on Computational Semantics (IWCS 2019), 23–33, 2019. [Paper]

• Yukiko Yana, Koji Mineshima and Daisuke Bekki. Variable Handling and Compositionality: Comparing DRT and DTS. Journal of Logic, Language and Information, Volume 28, Issue 2, 261–285, 2019. [Paper]

• Masashi Yoshikawa, Koji Mineshima, Hiroshi Noji, and Daisuke Bekki. Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference. Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), 7410-7417, 2019. [Paper] [arXiv] [Code]

• 鈴木莉子, 吉川将司, 谷中瞳, 峯島宏次, 戸次大介 「テキスト情報と画像情報を組み合わせた論理推論システムの構築」 第33回人工知能学会全国大会（朱鷺メッセ新潟コンベンションセンター）, 2019年. 全国大会優秀賞. [Paper] [Code]

• 谷中瞳, 戸次大介, 峯島宏次, 関根聡, 乾健太郎 「クラウドソーシングによる単調推論データセットの構築」 第33回人工知能学会全国大会（朱鷺メッセ新潟コンベンションセンター）, 2019年. [Paper]

• 窪田悠介, 峯島宏次, 林則序, 岡野伸哉 「汎用的な範疇文法ツリーバンクの構築」, 言語処理学会第25回年次大会発表論文集, C2-3, 143-146, 2019. [Paper]

• 吉川将司, 能地宏, 峯島宏次, 戸次大介 「係り受け木を用いたツリーバンク自動生成によるCCG解析分野適応」, 言語処理学会第25回年次大会発表論文集, F2-2, 197-200, 2019. [Paper]

• 大西舞子, 峯島宏次, 戸次大介 「CCGに基づく時間解析の実装に向けて」, 言語処理学会第25回年次大会発表論文集, D6-1, 1511-1514, 2019.

• 鈴木莉子, 谷中瞳, 峯島宏次, 戸次大介 「CCGと定理証明器を用いた画像情報の意味表現と推論の試み」 言語処理学会第25回年次大会発表論文集, D6-2, 1515-1518, 2019.

• 春田和泉, 峯島宏次, 戸次大介 「比較表現の意味解析と含意関係認識」, 言語処理学会第25回年次大会発表論文集, D6-3, 1519-1522, 2019.

• 谷中瞳, 峯島宏次, 戸次大介, 関根聡, 乾健太郎, Lasha Abzianidze, Johan Bos 「ニューラル自然言語推論に向けたMonotonicityに基づく含意関係認識データセット自動構築」, 言語処理学会第25回年次大会発表論文集, D6-5, 1527-1530, 2019. [Paper]

2018年

• Eriko Kinoshita, Koji Mineshima, and Daisuke Bekki. Coercion as Proof Search in Dependent Type Semantics. Alexandra Anna Spalek and Matthew Gotham (eds.) Approaches to Coercion and Polysemy, Oslo Studies in Language 10(2), 143–162, 2018. [Paper]

• Kana Manome, Masashi Yoshikawa, Hitomi Yanaka, Pascual Martínez-Gómez, Koji Mineshima and Daisuke Bekki. Neural sentence generation from formal semantics. Proceedings of the 11th International Conference on Natural Language Generation (INLG 2018), 408-414, 2018. [Paper]

• Ribeka Tanaka, Koji Mineshima and Daisuke Bekki. Paychecks, presupposition, and dependent types. Fifth Workshop on Natural Language and Computer Science (NLCS 2018) , Oxford University, Oxford, UK, July 7-8, 2018. [Paper]

• Hitomi Yanaka, Koji Mineshima, Pascual Martínez-Gómez and Daisuke Bekki. Acquisition of phrase correspondences using natural deduction proofs. Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT2018), 756–766, New Orleans, USA, June 1-6, 2018. [arXiv] [Paper]

• Masashi Yoshikawa, Koji Mineshima, Hiroshi Noji and Daisuke Bekki. Consistent CCG parsing over multiple sentences for improved logical reasoning. Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT2018), 407–412, New Orleans, USA, June 1-6, 2018. [arXiv] [Paper]

• 窪田悠介, 峯島宏次 「前提投射の実例のツリーバンクによる検索」, 日本言語学会第157回大会予稿集, [予稿集] [データ]

• 谷中瞳, 峯島宏次, Pascual Martínez-Gómez, 戸次大介 「自然演繹に基づく論理推論の文間類似度学習・含意関係認識への応用」, 自然言語処理, 25巻3号, 295-324頁, 2018年6月. [Paper]

• 外園康智, 長谷川貴博, 渡邉知樹, 馬目華奈, 簗有紀子, 谷中瞳, 田中リベカ, Pascual Martínez-Gómez, 峯島宏次, 戸次大介「意味解析システムccg2lambdaによる金融ドキュメント処理」 第32回人工知能学会全国大会（鹿児島・城山観光ホテル）JSAI2018論文集, 3G1-05, 2018年. [Paper]

• 吉川将司, 峯島宏次, 能地宏, 戸次大介 「知識ベース補完を用いた高階論理推論のための自動公理生成」 言語処理学会第24回年次大会発表論文集, E1-6, 113-116, 2018. [Paper]

• 馬目華奈, 谷中瞳, 吉川将司, 峯島宏次, 戸次大介 「RNN系列変換モデルを用いた高階論理式からの文生成」 言語処理学会第24回年次大会発表論文集, A3-3, 380-383, 2018. [Paper]

• 鈴木莉子, 高山沙也加, 北川舞, 田中リベカ, 峯島宏次, 戸次大介 「「NP1のNP2」の意味情報のアノテーション」 言語処理学会第24回年次大会発表論文集, C3-2, 424-427, 2018. [Paper] [Annotation Guideline]

• 谷中瞳, 峯島宏次, Pascual Martínez-Gómez, 戸次大介 「自然演繹に基づく文間の含意関係の証明を用いたフレーズアライメントの試み」 言語処理学会第24回年次大会発表論文集, E5-3, 983-986, 2018. [Paper]

• 馬目華奈, 外園康智, 長谷川貴博, 小西優祐, 渡邉知樹, 簗有紀子, 谷中瞳, 田中リベカ, 峯島宏次, 戸次大介 「含意関係認識による金融ドキュメントチェックへの取り組み」 言語処理学会第24回年次大会発表論文集, A6-5, 1159-1162, 2018. [Paper]

2017年

• Ribeka Tanaka, Koji Mineshima and Daisuke Bekki. Factivity and Presupposition in Dependent Type Semantics. Journal of Language Modelling. Vol.5, No.2, 385–420, 2017. [Paper]

• Ran Tian, Koji Mineshima and Pascual Martínez-Gómez. The Challenge of Composition in Distributional and Formal Semantics. Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP2017), 16-17, Taipei, Taiwan, November 27 – December 1, 2017. [Link] [Slides I] [Slides II]

• Hitomi Yanaka, Koji Mineshima, Pascual Martínez-Gómez and Daisuke Bekki. Determining Semantic Textual Similarity using Natural Deduction Proofs. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP2017), 681–691. Copenhagen, Denmark, September 7–11, 2017. [arXiv] [Paper]

• Dan Han, Pascual Martínez-Gómez and Koji Mineshima. Visual Denotations for Recognizing Textual Entailment. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP2017), 2843–2849. Copenhagen, Denmark, September 7–11, 2017. [paper]

• Yukiko Yana, Koji Mineshima and Daisuke Bekki. Variable Handling in DRT and DTS. Proceedings of the Workshop on Logic and Algorithms in Computational Linguistics 2017 (LACompLing2017), 131–159. Stockholm, August 16–19, 2017. [Proceedings]

• Pascual Martínez-Gómez, Koji Mineshima, Yusuke Miyao, and Daisuke Bekki. On-demand Injection of Lexical Knowledge for Recognising Textual Entailment. Proceedings of European Chapter of the Association for Computational Linguistics (EACL2017), 710–720, 2017. [Paper]

• Daisuke Bekki and Koji Mineshima. Context-Passing and Underspecification in Dependent Type Semantics. In S. Chatzikyriakidis and Z. Luo (eds.), Modern Perspectives in Type Theoretical Semantics, Studies of Linguistics and Philosophy, Springer, 11–41, 2017. [Link]

• 谷中瞳, 峯島宏次, Pascual Martínez-Gómez, 戸次大介 「単語の分散表現と仮説推論を用いた文の類似度学習」 第31回人工知能学会全国大会（ウインクあいち）JSAI2017論文集, 2B3-OS-07a-3, 2017年. [Paper]

• 簗有紀子, 峯島宏次, 戸次大介 「談話表示理論と依存型意味論における上書き問題」 言語処理学会第23回年次大会（筑波大学）発表論文集, D1-2, 62-65, 2017. [Paper]

• 伊藤友里菜, 峯島宏次, 戸次大介 「前提と慣習的含みに対する投射現象の分析」 言語処理学会第23回年次大会（筑波大学）発表論文集, D1-3, 66-69, 2017. [Paper]

• 谷中瞳, 峯島宏次, Pascual Martínez-Gómez, 戸次大介 「論理式による意味表現と証明プロセスに着目した文の類似度学習方法の提案」 言語処理学会第23回年次大会（筑波大学）発表論文集, B4-1, 378-381, 2017. [Paper]

2016年

• Kimi Kaneko, Saku Sugawara, Koji Mineshima and Daisuke Bekki. Annotation and Analysis of Discourse Relations, Temporal Relations and Multi-Layered Situational Relations in Japanese Texts. Proceedings of the 12th Workshop on Asian Language Resources (ALR12), 10–19, Coling2016 Workshop, Osaka, Japan, December 12, 2016. [Paper]

• Ribeka Tanaka, Koji Mineshima, and Daisuke Bekki. On the interpretation of dependent plural anaphora in a dependently-typed setting. Proceedings of the 13th International Workshop on Logic and Engineering of Natural Language Semantics (LENLS13), 86–99, 2016. [Proceedings]

• Eriko Kinoshita, Koji Mineshima, and Daisuke Bekki. An analysis of selectional restrictions with Dependent Type Semantics. Proceedings of the 13th International Workshop on Logic and Engineering of Natural Language Semantics (LENLS13), 100–113, 2016. [Proceedings]

• Koji Mineshima, Ribeka Tanaka, Pascual Martínez-Gómez, Yusuke Miyao, and Daisuke Bekki. Building compositional semantics and higher-order inference system for a wide-coverage Japanese CCG parser. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP2016), 2236–2242, Austin, Texas, November 1-5, 2016. [Paper] [Code]

• Yuri Sato and Koji Mineshima. Human reasoning with proportional quantifiers and its support by diagrams. Diagrammatic Representation and Inference, Lecture Notes in Computer Science, Volume 9781, 123–138, Springer-Verlag. 2016. [Link]

• Pascual Martínez-Gómez, Koji Mineshima, Yusuke Miyao, and Daisuke Bekki. ccg2lambda: a compositional semantics system. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL2016), System Demonstrations, 85–90, Berlin, Germany, August 7–12, 2016. [Paper] [Code]

• 田中リベカ, 峯島宏次, 戸次大介「依存型意味論による複数照応の分析」 第30回人工知能学会全国大会（北九州国際会議場）JSAI2016論文集, 2016年. [Paper]

• 木下恵梨子, 峯島宏次, 戸次大介「依存型意味論による述語の選択制限の前提としての分析」 第30回人工知能学会全国大会（北九州国際会議場）JSAI2016論文集, 2016年. [Paper]

• 木下恵梨子, 中村絢子, 峯島宏次, 戸次大介「依存型意味論とオントロジーを用いた論理的多義とコアーション現象の分析にむけて」 言語処理学会第22回年次大会（東北大学）発表論文集, D2-4, 429-432, 2016年. [Paper]

• 田中リベカ, 峯島宏次, Pascual Martínez-Gómez, 宮尾祐介, 戸次大介「日本語CCGパーザに基づく意味解析・推論システムの提案」 言語処理学会第22回年次大会（東北大学）発表論文集, D4-2, 757-760, 2016年. [Paper]

• 川添愛, 田中リベカ, 峯島宏次, 戸次大介「機能語の意味を表現する推論テストセット ーJSeMとりたて助詞テストの構築ー」 言語処理学会第22回年次大会（東北大学）発表論文集, B5-3, 817-820, 2016. [Paper]

2015年

• Yuri Sato and Koji Mineshima. How diagrams can support syllogistic reasoning: an experimental study. Journal of Logic, Language and Information. Volume 24, Issue 4, 409–455. 2015. [Link]

• Tsuyoshi Murata, Koji Mineshima, and Daisuke Bekki. (eds.) New Frontiers in Artificial Intelligence JSAI-isAI 2014 Workshops, LENLS, JURISIN, and GABA, Kanagawa, Japan, October 27-28, 2014, Revised Selected Papers. Lecture Notes in Computer Science, Volume 9067, 2015. Springer-Verlag. [Link]

• Ai Kawazoe, Ribeka Tanaka, Koji Mineshima and Daisuke Bekki. An inference problem set for evaluating semantic theories and semantic processing systems for Japanese. Proceedings of the Eleventh International Workshop on Logic and Engineering of Natural Language Semantics (LENLS12), 67–73, 2015. [Paper] [Dataset]

• Koji Mineshima, Pascual Martínez-Gómez, Yusuke Miyao, and Daisuke Bekki. Higher-order logical inference with compositional semantics. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP 2015), September 17-21, 2015, Lisbon, Portugal. 2055–2061. [Paper] [Code]

• Ribeka Tanaka, Koji Mineshima and Daisuke Bekki. Factivity and presupposition in dependent type semantics. Proceedings of TYpe Theory and LExical Semantics (TYTLES) in the 27th European Summer School in Logic, Language and Information (ESSLLI 2015), Barcelona, Spain. 2015. A revised and expanded version will appear in Journal of Language Modelling.

• Ayako Nakamura, Koji Mineshima, and Daisuke Bekki. Towards modeling natural language inferences with part-whole relations using formal ontology and lexical semantics. Proceedings of the FOfAI session of the Joint Ontology Workshops (JOWO), July 25-27th, Buenos Aires. 2015. [Paper]

• 峯島宏次「内包と外延」「命題」, 斎藤純男, 田口善久, 西村義樹 編 『明解言語学辞典』三省堂, 2015年.

• 川添愛, 田中リベカ, 峯島宏次, 戸次大介 「形式意味論に基づく含意関係テストセット構築の方法論」 第29回人工知能学会全国大会（公立はこだて未来大学）JSAI2015論文集, 2015年. [Paper]

• 中村絢子, 峯島宏次, 戸次大介 「オントロジーを用いた型理論的な語彙意味論の試み」 第29回人工知能学会全国大会（公立はこだて未来大学）JSAI2015論文集, 2015年. [Paper]

• 田中リベカ, 峯島宏次, 戸次大介 「依存型意味論による叙実動詞の意味記述の試み」 第29回人工知能学会全国大会（公立はこだて未来大学）JSAI2015論文集, 2015年. [Paper]

• 中村絢子, 峯島宏次, 戸次大介 「オントロジーを用いた自然言語の推論に向けて」 言語処理学会第21回年次大会（京都大学）発表論文集, D1-2, 309-312, 2015年. [Paper]

• 川添愛, 田中リベカ, 峯島宏次, 戸次大介 「日本語意味論テストセットの構築」 言語処理学会第21回年次大会（京都大学）発表論文集, E4-1, 704-707, 2015年. [Paper]

2014年

• Ribeka Tanaka, Koji Mineshima and Daisuke Bekki. Resolving modal anaphora in dependent type semantics. In Proceedings of the Eleventh International Workshop on Logic and Engineering of Natural Language Semantics (LENLS11), 54–67. 2014. A revised and expanded version appeared in Tsuyoshi Murata, Koji Mineshima, Daisuke Bekki (eds.), New Frontiers in Artificial Intelligence, Lecture Notes in Computer Science, Vol. 9067, 83–98. 2015. [Link]

• Koji Mineshima, Yuri Sato, Ryo Takemura and Mitsuhiro Okada. Towards explaining the cognitive efficacy of Euler diagrams in syllogistic reasoning: a relational perspective. Journal of Visual Languages and Computing. Volume 25, Issue 3. 156–169. 2014. [Link]

2013年

• Koji Mineshima. Aspects of Inference in Natural Language. PhD thesis, Keio University, 2013.

• 峯島宏次「変項名詞句の階層」, 西山佑司 編『名詞句の世界—その意味と解釈の神秘に迫る』所収, 第IV部第14章, 407-430頁, ひつじ書房, 2013年. [Link]

• 峯島宏次「自由拡充をどのように制約するか」, 西山佑司 編『名詞句の世界—その意味と解釈の神秘に迫る』所収, 第V部第18章, 513-557頁, ひつじ書房, 2013年. [Link]

2012年

• Koji Mineshima, Mitsuhiro Okada and Ryo Takemura. A generalized syllogistic inference system based on inclusion and exclusion relations. Studia Logica, Volume 100, Issue 4. (Special issue, Logic and Natural Language, edited by Nissim Francez and Ian Pratt-Hartmann.) 753–785. 2012. [Link]

• Koji Mineshima, Yuri Sato, Ryo Takemura and Mitsuhiro Okada. On the cognitive efficacy of Euler diagrams in syllogistic reasoning: a relational perspective. In P. Chapman and L. Micallef (eds.), Proceedings of the 3rd International Workshop on Euler Diagrams (Euler Diagrams 2012), CEUR Workshop Proceedings, Vol. 854, 17–31. 2012. Best Paper Award. [Link]

• Koji Mineshima, Mitsuhiro Okada and Ryo Takemura. A diagrammatic inference system with Euler circles. Journal of Logic, Language and Information, Volume 21, Issue 3. 365–391. 2012. [Link]

• Yuri Sato and Koji Mineshima. The efficacy of diagrams in syllogistic reasoning: a case of linear diagrams. In P. Rodgers, P. Cox and B. Plimmer (eds.), Proceedings of the 7th International Conference on the Theory and Application of Diagrams (Diagrams 2012), Lecture Notes in Computer Science, Vol. 7352, 352–355, Springer-Verlag, 2012. [Link]

2011年

• Yuri Sato, Koji Mineshima and Ryo Takemura. Interpreting logic diagrams: a comparison of two formulations of diagrammatic representations. Proceedings of 33rd Annual Conference of the Cognitive Science Society, 2182–2187, 2011. [Link]

• 佐藤有理, 峯島宏次, 竹村亮, 岡田光弘 「図形を用いた演繹的推論の認知プロセス」, 2011年度日本認知科学会第28回大会（東京大学）発表論文集, 269-274, 2011年. [Paper]

2010年

• Yuri Sato, Koji Mineshima and Ryo Takemura. The efficacy of Euler and Venn diagrams in deductive reasoning: empirical findings. In A.K. Goel, M. Jamnik, and N.H. Narayanan (eds.), Proceedings of the 6th International Conference on the Theory and Application of Diagrams (Diagrams 2010), Lecture Notes in Computer Science, Vol. 6170, 6–22, Springer-Verlag, 2010. [Link]

• Koji Mineshima, Mitsuhiro Okada and Ryo Takemura. Two types of diagrammatic inference system: natural deduction style and resolution style. In A.K. Goel, M. Jamnik, and N.H. Narayanan (eds.), Proceedings of the 6th International Conference on the Theory and Application of Diagrams (Diagrams 2010), Lecture Notes in Computer Science, Vol. 6170, 99–114, Springer-Verlag, 2010. [Link]

• Yuri Sato, Koji Mineshima and Ryo Takemura. Constructing internal diagrammatic proofs from external logic diagrams. Proceedings of 32nd Annual Conference of the Cognitive Science Society, 2668–2673, 2010. [Link]

• Yuri Sato, Koji Mineshima, and Ryo Takemura. Children's reasoning with logic diagrams. In David N. Rapp (ed.), Spatial Cognition 2010: Poster Presentations SFB/TR 8 Report No. 024-07/2010, 81–84. 2010. [Paper]

• Yuji Nishiyama and Koji Mineshima. Free enrichment and the over-generation problem. In Ewa Walaszewska et al. (eds.), In the Mind and Across Minds: A Relevance-Theoretic Perspective on Communication and Translation. Cambridge Scholars Publishing, 22–42, 2010.

• 竹村亮, 峯島宏次, 佐藤有理, 岡田光弘 「オイラー図・ヴェン図を用いた図形推論の証明論的分析」 第24回人工知能学会全国大会, JSAI2010論文集, 2010年. [Paper]

2009年以前

• Koji Mineshima, Mitsuhiro Okada and Ryo Takemura. Conservativity for a hierarchy of Euler and Venn reasoning systems. Proceedings of Visual Languages and Logic 2009. CEUR Series Vol. 510, 37–61, 2009. [Link]

• 峯島宏次「自然言語の論理と日本語の意味論」, 飯田隆 編 『岩波講座哲学 第三巻 言語／思考の哲学』所収, 139-170頁, 岩波書店, 2009年.

• 岡田光弘, 峯島宏次「モデル論的意味論と完全性定理」「直観主義論理と型理論」「論理的計算理論」「動的状態変化と論理」「論理と哲学」, 言語処理学会 編『言語処理学事典』共立出版, 2009年.

• Koji Mineshima. A presuppositional analysis of definite descriptions in proof theory. In Ken Satoh et al. (eds.), New Frontiers in Artificial Intelligence: JSAI 2007 Conference and Workshops, Revised Selected Papers, Lecture Notes in Computer Science Vol. 4914, 214–227, Springer-Verlag. 2008. [Link]

• Koji Mineshima, Mitsuhiro Okada, Yuri Sato and Ryo Takemura. Diagrammatic reasoning system with Euler circles: theory and experiment design. G. Stapleton et al. (eds.), Proceedings of the 5th international conference on Diagrammatic Representation and Inference (Diagrams 2008), Lecture Notes in Computer Science, Vol. 5223, 188–205, Springer-Verlag, 2008. [Link]

• Yuji Nishiyama and Koji Mineshima. Property expressions and the semantics-pragmatics interface. In Piotr Cap and Joanna Nijakowska (eds.), Current Trends in Pragmatics, Cambridge Scholars Publishing, 130–151. 2007.

• 西山佑司, 峯島宏次 「叙述名詞句と語用論的解釈—自由拡充プロセスにたいする意味論的制約をめぐって」, 飯田隆 編『西洋精神史における言語と言語観—継承と創造』所収, 21-50頁, 慶應義塾大学言語文化研究所, 2006年.

• 峯島宏次「自然言語と論理」, 飯田隆 編『論理の哲学』所収, 213-241頁, 講談社, 2005年.

• W.ライカン『言語哲学—入門から中級まで』 荒磯敏文, 川口由起子, 鈴木生郎, 峯島宏次（共訳）, 勁草書房, 2005年. [Link]

Link

• 岡田研究室（慶應義塾大学文学部哲学専攻）
• 戸次研究室（お茶の水女子大学理学部情報科学科）