Activities

Publication

International conferences/workshops

1. Irfan Robbani, Paul Reisert, Surawat Pothong, Naoya Inoue, Camélia Guerraoui, Wenzhi Wang, Shoichi Naito, Jungmin Choi, Kentaro Inui. Flee the Flaw: Annotating the Underlying Logic of Fallacious Arguments Through Templates and Slot-filling. To appear in Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), November 2024.

2. Shoichi Naito, Wenzhi Wang, Paul Reisert, Naoya Inoue, Camélia Guerraoui, Kenshi Yamaguchi, Jungmin Choi, Irfan Robbani, Surawat Pothong, Kentaro Inui. Designing Logic Pattern Templates for Counter-Argument Logical Structure Analysis. To appear in Findings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), November 2024.

3. Yuting Shi, Naoya Inoue, Houjing Wei, Yufeng Zhao and Tao JIN. Find-the-Common: A Benchmark for Explaining Visual Patterns from Images. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING2024), May 2024.

4. Ai Ishii, Naoya Inoue, Hisami Suzuki and Satoshi Sekine. JEMHopQA: Dataset for Japanese Explainable Multi-Hop Question Answering. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING2024), May 2024.

5. Daichi Haraguchi, Kiyoaki Shirai, Naoya Inoue and Natthawut Kertkeidkachorn. Discovering Highly Influential Shortcut Reasoning: An Automated Template-Free Approach. In Findings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP2023), pp. 6401-6407, December 2023. paper

6. Camélia Guerraoui, Paul Reisert, Naoya Inoue, Farjana Sultana Mim, Shoichi Naito, Jungmin Choi, Irfan Robbani, Wenzhi Wang and Kentaro Inui. Teach Me How to Argue: A Survey on NLP Feedback Systems in Argumentation. In Proceedings of the 10th Workshop on Argumentation Mining (ArgMining2023), pp. 19-34, December 2023. paper

7. Hoai Linh Luu and Naoya Inoue. Counterfactual Adversarial Training for Improving Robustness of Pre-trained Language Models. In Proceedings of Pacific Asia Conference on Language, Information and Computation (PACLIC 37). 9 pages, December 2023.

8. Vasudha Varadarajan, Nikita Soni, Weixi Wang, Christian Luhmann, H. Andrew Schwartz and Naoya Inoue. Detecting Dissonant Stance in Social Media: The Role of Topic Exposure. In Proceedings of the Fifth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS), pp.151-156, November 2022.

9. Keshav Singh, Naoya Inoue, Farjana Sultana Mim, Shoichi Naito and Kentaro Inui. IRAC: A Domain-specific Annotated Corpus of Implicit Reasoning in Arguments. In Proceedings of the 13th Language Resources and Evaluation Conference (LREC2022), pp. 4674-4683, June 2022. paper

10. Farjana Sultana Mim, Naoya Inoue, Shoichi Naito, Keshav Singh and Kentaro Inui. LPAttack: A Feasible Annotation Scheme for Capturing Logic Pattern of Attacks in Arguments. In Proceedings of the 13th Language Resources and Evaluation Conference (LREC2022), pp. 2446-2459, June 2022. paper

11. Shoichi Naito, Shintaro Sawada, Chihiro Nakagawa, Naoya Inoue, Kenshi Yamaguchi, Iori Shimizu, Farjana Sultana Mim, Keshav Singh and Kentaro Inui. TYPIC: A Corpus of Template-Based Diagnostic Comments on Argumentation. In Proceedings of the 13th Language Resources and Evaluation Conference (LREC2022), pp. 5916-5928, June 2022. paper

12. Naoya Inoue, Charuta Pethe, Allen Kim and Steve Skiena. Learning and Evaluating Character Representations in Novels. In Findings of the Association for Computational Linguistics: ACL2022, May 2022. paper

13. Keshav Singh, Farjana Sultana Mim, Naoya Inoue, Shoichi Naito and Kentaro Inui. Exploring Methodologies for Collecting High-Quality Implicit Reasoning in Arguments. In Proceedings of the 8th Workshop on Argument Mining (ArgMining), November 2021, pp.57-66. paper

14. Naoya Inoue, Harsh Trivedi, Steven Sinha, Niranjan Balasubramanian and Kentaro Inui. Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), November 2021, pp.6064-6080. paper repo

15. Allen Kim, Charuta Pethe, Naoya Inoue and Steve Skiena. Cleaning Dirty Books: Post-OCR Processing for Previously Scanned Texts. In Findings of the Association for Computational Linguistics: EMNLP2021, November 2021. pp.4217-4226. paper

16. Qin Dai, Naoya Inoue, Ryo Takahashi and Kentaro Inui. Two Training Strategies for Improving Relation Extraction over Universal Graph. In Proceedings of the 16th conference of the European Chapter of the Association for Computational Linguistics (EACL2021), April 2021, pp.3673-3684. paper

17. Takaki Otake, Sho Yokoi, Naoya Inoue, Ryo Takahashi, Tatsuki Kuribayashi and Kentaro Inui. Modeling Event Salience in Narratives via Barthes’ Cardinal Functions. In The 28th International Conference on Computational Linguistics (COLING2020), December 2020, pp.1784–1794. paper

18. Naoya Inoue, Pontus Stenetorp and Kentaro Inui. R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL2020), July 2020, pp.6740–6750. paper slides/video website

19. Pride Kavumba, Naoya Inoue (equal contribution), Benjamin Heinzerling, Keshav Singh, Paul Reisert and Kentaro Inui. When Choosing Plausible Alternatives, Clever Hans can be Clever. In Proceedings of the First Workshop on COmmonsense INference in Natural Language Processing (COIN2019), November 2019. pp.33-42, paper website

20. Keshav Singh, Paul Reisert, Naoya Inoue, Pride Kavumba and Kentaro Inui. Improving Evidence Detection by Leveraging Warrants. In Proceedings of the Second Workshop on Fact Extraction and Verification (FEVER2019), pp.57-62, November 2019. paper

21. Tianqi Wang, Naoya Inoue, Hiroki Ouchi, Tomoya Mizumoto and Kentaro Inui. Inject Rubrics into Short Answer Grading System. In Proceedings of the Second Workshop on Deep Learning for Low-resource NLP (DeepLo2019), pp.175–182, November 2019. paper

22. Qin Dai, Naoya Inoue, Paul Reisert, Ryo Takahashi and Kentaro Inui. Incorporating Chains of Reasoning over Knowledge Graph for Distantly Supervised Biomedical Knowledge Acquisition. In Proceedings of the 33rd Pacific Asia Conference on Language, Information and Computation (PACLIC 33), pp. 19-28, September 2019.

23. Farjana Sultana Mim, Naoya Inoue, Paul Reisert, Hiroki Ouchi and Kentaro Inui. Unsupervised Learning of Discourse-Aware Text Representation for Essay Scoring. In Proceedings of the 2019 ACL Student Research Workshop (SRW), August 2019. paper

24. Tatsuki Kuribayashi, Hiroki Ouchi, Naoya Inoue, Paul Reisert, Toshinori Miyoshi, Jun Suzuki and Kentaro Inui. An Empirical Study of Span Representations in Argumentation Structure Parsing. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), August 2019. paper

25. Hono Shirai, Naoya Inoue, Jun Suzuki and Kentaro Inui. Annotating with Pros and Cons of Technologies in Computer Science Papers. In Proceedings of First Workshop on Extracting Structured Knowledge from Scientific Publications (ESSP), June 2019. paper website

26. Qin Dai, Naoya Inoue, Paul Reisert, Ryo Takahashi and Kentaro Inui. Distantly Supervised Biomedical Knowledge Acquisition via Knowledge Graph Based Attention. In Proceedings of First Workshop on Extracting Structured Knowledge from Scientific Publications (ESSP), June 2019. paper

27. Paul Reisert, Gisela Vallejo, Naoya Inoue, Iryna Gurevych and Kentaro Inui. An Annotation Protocol for Collecting User-Generated Counter-Arguments using Crowdsourcing. In Proceedings of the 20th International Conference on Artificial Intelligence in Education (AIED), June 2019. paper

28. Qin Dai, Naoya Inoue, Paul Reisert and Kentaro Inui. Scientific Knowledge Acquisition via the Interaction between Relation Extraction and Knowledge Graph Completion. In Proceedings of Third International Workshop on SCIentific DOCument Analysis (SCIDOCA), November 2018. paper

29. Qin Dai, Naoya Inoue, Paul Reisert and Kentaro Inui. Improving Scientific Relation Classification with Task Specific Supersense. In Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computing (PACLIC32), December 2018. paper

30. Paul Reisert, Naoya Inoue, Tatsuki Kuribayashi, and Kentaro Inui. Feasible Annotation Scheme for Capturing Policy Argument Reasoning using Argument Templates. In Proceedings of the 5th Workshop on Argumentation Mining, November 2018. paper

31. Daiqin, Naoya Inoue, Paul Reisert, and Kentaro Inui. Leveraging Document-specific Information for Identifying Relations in Scientific Articles. In Proceedings of Second International Workshop on SCIentific DOCument Analysis (SCIDOCA), November 2017. paper

32. Reina Akama, Kazuaki Inada, Naoya Inoue, Sosuke Kobayashi, and Kentaro Inui. Generating Stylistically Consistent Dialog Responses with Transfer Learning. In Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP), pp.408-412, November 2017. paper

33. Shota Sasaki, Sho Takase, Naoya Inoue, Naoaki Okazaki, and Kentaro Inui. Handling Multiword Expressions in Causality Estimation. In Proceedings of 12th International Conference on Computational Semantics (IWCS), September 2017. paper implementation

34. Naoya Inoue and Andrew S. Gordon. A Scalable Weighted Max-SAT Implementation of Propositional Etcetera Abduction. In Proceedings of the 30th International Florida Artificial Intelligence Research Society Conference (FLAIRS), pp.62-67, May 2017. paper slides

35. Melissa Roemmele, Sosuke Kobayashi, Naoya Inoue and Andrew Gordon. An RNN-based Binary Classifier for the Story Cloze Test. In Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics (LSDSem; EACL Workshop), pp.74-80, April 2017. paper

36. Naoya Inoue, Yuichiro Matsubayashi, Masayuki Ono, Naoaki Okazaki and Kentaro Inui. Modeling Context-sensitive Selectional Preference with Distributed Representations. In Proceedings of the 26th International Conference on Computational Linguistics (COLING), pp.2829–2838, December 2016. paper poster

37. Paul Reisert, Naoya Inoue, Naoaki Okazaki, and Kentaro Inui. Towards Recognizing Logic in Argumentative Texts (Extended Abstract). First International Workshop on SCIentific DOCument Analysis (SCIDOCA), November 2016.

38. Naoya Inoue, Yasutaka Kuriya, Sosuke Kobayashi, and Kentaro Inui. Recognizing potential traffic risks through logic-based deep scene understanding. In Proceedings of the 22nd ITS World Congress (ITSWC), October 2015. paper (draft) slides

39. Paul Reisert, Naoya Inoue, Naoaki Okazaki, and Kentaro Inui. A Computational Approach for Generating Toulmin Model Argumentation. In Proceedings of the 2nd Workshop on Argumentation Mining, pp.45–55, June 2015. paper

40. Canasai Kruengkrai, Naoya Inoue, Jun Sugiura, and Kentaro Inui. An Example-Based Approach to Difficult Pronoun Resolution. In Proceedings of the 28th Pacific Asia Conference on Language, Information and Computing (PACLIC), pp.358-367, December 2014. paper

41. Jun Sugiura, Naoya Inoue and Kentaro Inui. Recognizing Implicit Discourse Relations through Abductive Reasoning with Large-scale Lexical Knowledge. In Proceedings of the 1st Workshop on Natural Language Processing and Automated Reasoning (NLPAR), September 2013. paper

42. Kazeto Yamamoto, Naoya Inoue, Yotaro Watanabe, Naoaki Okazaki, and Kentaro Inui. Discriminative Learning of First-order Weighted Abduction from Partial Discourse Explanations. In Proceedings of the 14th International Conference on Intelligent Text Processing and Computational Linguistics (CICLING), pp.545-558, March 2013. paper

43. Naoya Inoue, Ekaterina Ovchinnikova, Kentaro Inui, and Jerry R. Hobbs. Coreference Resolution with ILP-based Weighted Abduction. In Proceedings of the 24th International Conference on Computational Linguistics (COLING), pp.1291-1308, December 2012. paper slides

44. Naoya Inoue and Kentaro Inui. Large-scale Cost-based Abduction in Full-fledged First-order Predicate Logic with Cutting Plane Inference. In Proceedings of the 13th European Conference on Logics in Artificial Intelligence (JELIA), pp.281-293, September 2012. paper slides

45. Naoya Inoue and Kentaro Inui. ILP-based Reasoning for Weighted Abduction. In Proceedings of AAAI Workshop on Plan, Activity and Intent Recognition (PAIR), pp. 25-32, August 2011. paper slides

46. Naoya Inoue, Ryu Iida, Kentaro Inui, and Yuji Matsumoto. Resolving Direct and Indirect Anaphora for Japanese Definite Noun Phrases. In Proceedings of the Conference of the Pacific Association for Computational Linguistics (PACLING), pp.268-273, September 2009. paper slides

Journal papers

1. Qin Dai, Benjamin Heinzerling, Naoya Inoue, Kentaro Inui. Universal Graph based Distantly Supervised Relation Extraction. Journal of Natural Language Processing, Vol. 29, pp. 1138-1164, 2022.

2. Farjana Sultana Mim, Naoya Inoue, Paul Reisert, Hiroki Ouchi, Kentaro Inui. Corruption Is Not All Bad: Incorporating Discourse Structure into Pre-training via Corruption for Essay Scoring. IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol. 29, pp. 2202-2215, June 2021. paper

3. 栗林 樹生，大内 啓樹，井之上 直也，鈴木 潤，Paul Reisert，三好 利昇，乾 健太郎. 論述構造解析におけるスパン分散表現. 自然言語処理 Vol.27, No.4, December 2020. paper (言語処理学会 2020年度最優秀論文賞)

4. Tadahiro Taniguchi, Daichi Mochihashi, Takayuki Nagai, Satoru Uchida, Naoya Inoue, Ichiro Kobayashi, Tomoaki Nakamura, Yoshinobu Hagiwara, Naoto Iwahashi, Tetsunari Inamura. Survey on Frontiers of Language and Robotics. Advanced Robotics, Vol. 33, No. 12, 31 pages, June 2019. paper

5. Qin Dai, Naoya Inoue, Paul Reisert, and Kentaro Inui. Leveraging Unannotated Texts for Scientific Relation Extraction. IEICE Transactions on Information and Systems, Vol. E101-D, No. 12, pp.3209-3217, December 2018. paper

6. Paul Reisert, Naoya Inoue, Naoaki Okazaki, and Kentaro Inui. Designing a Task for Recognizing Argumentation Logic in Argumentative Texts. International Journal of Computational Linguistics and Applications, 2017.

7. Paul Reisert, Naoya Inoue, Naoaki Okazaki, and Kentaro Inui. Identifying and Ranking Relevant Claims for Decision Support. International Journal of Computational Linguistics and Applications, 2017.

8. Ryo Takahashi, Naoya Inoue, Yasutaka Kuriya, Sosuke Kobayashi, and Kentaro Inui. Explaining potential risks in traffic scenes by combining logical inference and physics simulation. International Journal of Machine Learning and Computing, Vol. 6, No. 5, pp. 248-255, October 2016. paper

9. 山本風人, 井之上直也, 乾健太郎. 機能的なリテラルを含む公理体系における仮説推論の効率化. 自然言語処理 Vol.23, No.3, pp.267-298, June 2016. paper

10. Kazeto Yamamoto, Naoya Inoue, Kentaro Inui, Yuki Arase and Jun’ichi Tsujii. Boosting the Efficiency of First-order Abductive Reasoning Using Pre-estimated Relatedness between Predicates. International Journal of Machine Learning and Computing, Vol. 5, No. 2, pp. 114-120, April 2015. paper

11. Naoya Inoue and Kentaro Inui. ILP-based Inference for Cost-based Abduction on First-order Predicate Logic. Journal of Natural Language Processing, Vol.20, No.5, pp.629-656, December 2013. paper

12. 飯田龍, 小町守, 井之上直也, 乾健太郎, 松本裕治. 述語項構造と照応関係のアノテーション: NAISTテキストコーパス構築の経験から. 自然言語処理, Vol.17, No.2, pp.25-50, April 2010. (言語処理学会 20周年記念論文賞) paper

13. Naoya Inoue, Ryu Iida, Kentaro Inui, and Yuji Matsumoto. Resolving Direct and Indirect Anaphora for Japanese Definite Noun Phrases. Journal of Natural Language Processing, Vol.17, No.1, pp.221-246, January 2010. paper

Book chapter

1. 井之上 直也（分担: 第7章）. コミュニケーションの言語処理: 人工知能による議論の支援. 谷口 忠大, 石川 竜一郎 (編著), コミュニケーション場のメカニズムデザイン, 慶應義塾大学出版会, 2021年10月. info

2. 井之上 直也（分担: 1.4章）. 自然言語を中心とする記号処理. 独立行政法人情報処理推進機構 AI白書編集委員会, AI白書 2017, 株式会社角川アスキー総合研究所発行, 2017年7月. info

3. Ryu Iida, Mamoru Komachi, Naoya Inoue, Kentaro Inui and Yuji Matsumoto. NAIST Text Corpus: Annotating Predicate-Argument and Coreference Relations in Japanese. In Nancy Ide and James Pustejovsky (Eds), Handbook of Linguistic Annotation, Part II, pp.1177-1196, Springer, July 2017. info

4. Naoya Inoue, Ekaterina Ovchinnikova, Kentaro Inui, and Jerry R. Hobbs. Weighted Abduction for Discourse Processing Based on Integer Linear Programming. In Gita Sukthankar, Christopher Geib, Robert P. Goldman, Hung Bui, and David V. Pynadath (Eds), Plan, Activity, and Intent Recognition, Chapter 2, pp.33-55, Elsevier, March 2014. info

Review articles

1. 乾 健太郎, 石井 雄隆, 松林 優一郞, 井之上 直也, 内藤 昭一, 磯部 順子, 舟山 弘晃, 菊地 正弥. 自然言語処理×教育における説明能力 -説明できるライティング評価技術への新しい展開-. 2023 年 16 巻 4 号 p. 289-300. 電子情報通信学会 基礎・境界ソサイエティ Fundamentals Review, 2023.

2. 井之上 直也. 言語処理学会第 27 回年次大会ワークショップ 「若手研究者交流のニューノーマルを考える」開催報告. 自然言語処理, Vol. 28, No. 3, pp. 901-906, 2021. article

3. 井之上 直也. R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason. 自然言語処理, Vol. 27, No. 3, pp. 665-670, 2020. article

4. 井之上 直也. 言語データからの知識獲得と言語処理への応用. 人工知能, Vol. 33, No. 3, pp. 337-344, 2018. article

Preprint papers

1. Camélia Guerraoui, Paul Reisert, Naoya Inoue, Farjana Sultana Mim, Shoichi Naito, Jungmin Choi, Irfan Robbani, Wenzhi Wang, Kentaro Inui. Teach Me How to Improve My Argumentation Skills: A Survey on Feedback in Argumentation. arXiv preprint, 14 pages, July 2023.

2. Pride Kavumba, Naoya Inoue, Benjamin Heinzerling, Keshav Singh, Paul Reisert, Kentaro Inui. When Choosing Plausible Alternatives, Clever Hans can be Clever. arXiv preprint. paper

3. Keshav Singh, Paul Reisert, Naoya Inoue, Kentaro Inui. A Comparative Study on Collecting High-Quality Implicit Reasonings at a Large-scale. arXiv preprint. paper

4. Qin Dai, Naoya Inoue, Ryo Takahashi, Kentaro Inui. Two Training Strategies for Improving Relation Extraction over Universal Graph. arXiv preprint. paper

5. Farjana Sultana Mim, Naoya Inoue, Paul Reisert, Hiroki Ouchi, Kentaro Inui. Corruption Is Not All Bad: Incorporating Discourse Structure into Pre-training via Corruption for Essay Scoring. paper

6. Takaki Otake, Sho Yokoi, Naoya Inoue, Ryo Takahashi, Tatsuki Kuribayashi, Kentaro Inui. Modeling Event Salience in Narratives via Barthes’ Cardinal Functions. paper

7. Naoya Inoue, Pontus Stenetorp, Kentaro Inui. R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason. arXiv preprint. paper

8. Paul Reisert, Benjamin Heinzerling, Naoya Inoue, Shun Kiyono, Kentaro Inui. Riposte! A Large Corpus of Counter-Arguments. arXiv preprint. paper

9. Paul Reisert, Naoya Inoue, Naoaki Okazaki, and Kentaro Inui. A Corpus of Deep Argumentative Structures as an Explanation to Argumentative Relations. arXiv preprint. paper

Domestic conferences

1. 加藤 万理子, 趙 羽風, 閻 真竺, 石 钰婷, 井之上 直也. 画像特徴ベクトルは重みを固定した言語モデルで情報豊かなトークンである. 第19回YANSシンポジウム, September 2024.

2. WEI Houjing, SHI Yuting, Cho Hakaze, YAN Zhenzhu, Naoya Inoue. Phase Diagram of Vision Large Language Models Inference: A Perspective from Interaction across Image and Instruction. 第19回YANSシンポジウム, September 2024.

3. 趙 羽風, 坂井 吉弘, 加藤 万理子, 井之上 直也. StaICC: 文脈内学習における分類タスクの標準的なベンチマーク. 第19回YANSシンポジウム, September 2024.

4. 趙 羽風, 坂井 吉弘, 加藤 万理子, 田中 健史朗, 石井 晶, 井之上 直也. In-Context Learningにおけるトークンベース較正手法の用いる決定境界は最適でない. 研究報告自然言語処理 (NL), Vol. 2024-NL-260, No. 14, 17 pages, June 2024.

5. Surawat Pothong, Paul Reisert, Naoya Inoue, Irfan Robbani, Camélia Guerraoui, Wenzhi Wang, Shoichi Naito, Jungmin Choi, and Kentaro Inui. Towards a Benchmark Dataset for Stress-testing Fallacy Detection Models. 研究報告自然言語処理 (NL), Vol. 2024-NL-260, No. 18, 6 pages, June 2024.

6. 天野祥太郎, 中川智皓, 内藤昭一, 井之上直也, 山口健史, 尾崎大晟, 新谷篤彦. 大規模言語モデルの生成反論文のテンプレート追従性. 人工知能学会全国大会 (第38回) 論文集, 4 pages, June 2024.

7. 尾崎大晟, 中川智皓, 内藤昭一, 井之上直也, 山口健史, 天野祥太郎, 新谷篤彦. LLM による前提生成ステップを用いた反論の攻撃力向上. 人工知能学会全国大会 (第38回) 論文集, 4 pages, June 2024.

8. 趙羽風, 坂井吉弘, 井之上直也. NoisyICL: A Little Noise in Model Parameters Can Calibrate In-context Learning. 言語処理学会第30回年次大会論文集, 4 pages, March 2024.

9. Yuting Shi, Houjing Wei, Jin Tao, Yufeng Zhao, and Naoya Inoue. Find-the-Common: Benchmarking Inductive Reasoning Ability on Vision-Language Models. 言語処理学会第30回年次大会論文集, 4 pages, March 2024.

10. Bowen Gao, Shotaro Kitamura, and Naoya Inoue. Exploring the Challenges of Multi-Step Logical Reasoning with Language Models: A Few-Shot Approach to Explainable Entailment Trees. 言語処理学会第30回年次大会論文集, 4 pages, March 2024.

11. Irfan Robbani, Paul Reisert, Naoya Inoue, Surawat Pothong, Camélia Guerraoui, Wenzhi Wang, Shoichi Naito, Jungmin Choi, , and Kentaro Inui. Templates for Fallacious Arguments Towards Deeper Logical Error Comprehension. 言語処理学会第30回年次大会論文集, 4 pages, March 2024.

12. 坂井吉弘, 趙羽風, 井之上直也. In-context Learning においてLLMはフォーマットを学べるか. 言語処理学会第30回年次大会論文集, 4 pages, March 2024. (スポンサー賞)

13. 井之上直也, 原口大地, 田中健史朗, 白井清昭, Natthawut Kertkeidkachorn. 自己認知は LM as KB の信頼性を高めるか. 言語処理学会第30回年次大会論文集, 4 pages, March 2024. (優秀賞)

14. Wenzhi Wang, Shoichi Naito, Paul Reisert, Naoya Inoue, Camélia Guerraoui, Jungmin Choi, Irfan Robbani, and Kentaro Inui. Exploring Task Decomposition for Assisting Large Language Models in Counter-argument Logical Structure Analysis. 言語処理学会第30回年次大会論文集, 4 pages, March 2024.

15. Camélia Guerraoui, Paul Reisert, Naoya Inoue, Wenzhi Wang, Shoichi Naito, Jungmin Choi, Irfan Robbani, and Kentaro Inui. ArgVantage: the New Pedagogical System to Learn Argumentation. 言語処理学会第30回年次大会論文集, 4 pages, March 2024.

16. 内藤昭一, 王文質, Paul Reisert, 井之上直也, Camélia Guerraoui, 山口健史, Jungmin Choi, Irfan Robbani, 乾健太郎. 反論の論理パターン解析: データセット構築と実現性検証. 言語処理学会第30回年次大会論文集, 4 pages, March 2024.

17. 石井愛, 井之上直也, 鈴木久美, 関根聡. JEMHopQA:日本語マルチホップQAデータセットの改良. 言語処理学会第30回年次大会論文集, 4 pages, March 2024.

18. 石井愛, 井之上直也, 鈴木久美, 関根聡. マルチホップQAの根拠情報を用いたLLMの``偽''正解の分析. 言語処理学会第30回年次大会論文集, 4 pages, March 2024.

19. 関根聡, 安藤まや, 後藤美知子, 鈴木久美, 河原大輔, 井之上直也, 乾健太郎. ichikara-instruction: LLMのための日本語インストラクションデータの作成. 言語処理学会第30回年次大会論文集, 4 pages, March 2024. (委員特別賞)

20. 尾崎大晟, 中川智皓, 井之上直也, 内藤昭一, 山口健史, 天野祥太朗, 新谷篤彦. 大規模言語モデルを用いた有効反論箇所としての前提生成. 言語処理学会第30回年次大会論文集, 4 pages, March 2024.

21. 田中 健史朗, 戸次 大介, 井之上 直也. 論理的に同値なデータ拡張による言語モデルの頑健性向上. 研究報告自然言語処理 (NL), Vol. 2024-NL-259, No. 22, 7 pages, March 2024.

22. 前田雄之介, 岡田将吾, 井之上 直也. 就職面接訓練においてPREP話法が面接評価に与える影響の分析. 第100回 言語・音声理解と対話処理研究会（SLUD）, 6 pages, February 2024.

23. 尾崎大晟, 中川智皓, 内藤昭一, 井之上直也, 山口健史. 大規模言語モデルが生成した反論文の品質評価. 人工知能学会全国大会 (第37回) 論文集, 4 pages, June 2023. paper. (全国大会優秀賞/JSAI Annual Conference Award)

24. 前田雄之介, 井之上直也, 岡田将吾. 就職面接における発話内容のPREPアノテーション分析. 人工知能学会全国大会 (第37回) 論文集, 4 pages, June 2023. paper

25. 原口大地, 白井清昭, 井之上直也. 一般性を考慮した言語処理モデルのShortcut Reasoningの自動検出. 言語処理学会第29回年次大会論文集, 4 pages, March 2023. paper

26. 石井愛, 井之上直也, 関根聡. 根拠を説明可能な質問応答システムのための日本語マルチホップQAデータセット構築. 言語処理学会第29回年次大会論文集, 4 pages, March 2023. paper github

27. 大内啓樹, 進藤裕之, 若宮翔子, 松田裕貴, 井之上直也, 東山翔平, 中村哲, 渡辺太郎. 地球の歩き方旅行記データセット. 言語処理学会第29回年次大会論文集, 4 pages, March 2023.

28. Camélia Guerraoui, Paul Reisert, Keshav Singh, Farjana Sultana Mim, Naoya Inoue, Shoichi Naito, Wenzhi Wang, Kentaro Inui. Explain to Me What Is Wrong With My Arguments: A Survey about Explanations in Argumentation. 言語処理学会第29回年次大会論文集, 4 pages, March 2023. paper

29. Keshav Singh, Naoya Inoue, Paul Reisert, Farjana Sultana Mim, Shoichi Naito, Camélia Guerraoui, Wenzhi Wang, Kentaro Inui. Improving Evidence Detection with Domain-specific Implicit Reasonings. 言語処理学会第29回年次大会論文集, 4 pages, March 2023. paper

30. Wenzhi Wang, Paul Reisert, Naoya Inoue, Shoichi Naito, Camélia Guerraoui, Keshav Singh, Kentaro Inui. Towards Creating Analytic Dimensions for Evaluating the Quality of Debate Counter-Arguments. 言語処理学会第29回年次大会論文集, 4 pages, March 2023. paper

31. Keshav Singh, Naoya Inoue, Farjana Sultana Mim, Shoichi Naito and Kentaro Inui. Towards Explicating Implicit Reasoning in Arguments. NLP若手の会 第17回シンポジウム, August 2022.

32. 王文質, Farjana Sultana Mim, 内藤昭一, Keshav Singh, 井之上直也, 乾健太郎. 論述文の深い論理構造の自動解析に向けて. NLP若手の会 第17回シンポジウム, August 2022.

33. 原口大地, 白井清昭, 井之上直也. 論理的根拠に基づく頑健な機械読解に向けて. NLP若手の会 第17回シンポジウム, August 2022.

34. 内藤昭一, 澤田慎太郎, 中川智皓, 井之上直也, 乾健太郎. 論述への説明性の高いフィードバック提示に向けたコーパスの試作. 言語処理学会第27回年次大会論文集, 4 pages, March 2021.

35. 大竹孝樹, 横井祥, 井之上直也, 高橋諒, 栗林樹生, 乾健太郎. 物語におけるイベントの顕現性推定と物語類似性計算への応用. 言語処理学会第27回年次大会論文集, 4 pages, March 2021.

36. Pride Kavumba, Ana Brassard, Benjamin Heinzerling, Naoya Inoue, Kentaro Inui. None the wiser? Adding “None” Mitigates Superficial Cues in Multiple-Choice Benchmarks. 言語処理学会第27回年次大会論文集, 4 pages, March 2021.

37. Keshav Singh, Paul Reisert, Naoya Inoue, Kentaro Inui. Towards Understanding Implicit Reasoning in Arguments via Multiple Warrants. 言語処理学会第27回年次大会論文集, 4 pages, March 2021.

38. 花安 勇人, 池田 駿介, 久保寺 誠, 井之上 直也. 表面的手がかり語への依存軽減による論述関係認識モデルの汎化. 人工知能学会全国大会 (第34回) 論文集, 4 pages, June 2020.

39. 井之上 直也, Pontus Stenetorp, 乾 健太郎. 機械読解システムの推論過程のベンチマークの構築. 言語処理学会第26回年次大会論文集, 4 pages, March 2020. paper website (言語資源賞) poster

40. 大竹 孝樹, 横井 祥, 井之上 直也, 高橋 諒, 栗林 樹生, 乾 健太郎. 言語モデルによる物語中のイベントの顕現性推定. 言語処理学会第26回年次大会論文集, 4 pages, March 2020.

41. 内藤 昭一, 井之上 直也, 乾 健太郎. 論述構造解析における事前学習済み言語モデルの有効性検証. 言語処理学会第26回年次大会論文集, 4 pages, March 2020.

42. 高橋 諒, 井之上 直也, 谷中 瞳, 乾 健太郎. 知識ベースとテキストの構成的同時学習. 言語処理学会第26回年次大会論文集, 4 pages, March 2020.

43. Pride Kavumba, Naoya Inoue (equal contribution), Benjamin Heinzerling, Keshav Singh, Paul Reisert, Kentaro Inui. Balanced COPA: Countering Superficial Cues in Causal Reasoning. 言語処理学会第26回年次大会論文集, 4 pages, March 2020.

44. 鈴木正敏, 鈴木潤, 松田耕史, ⻄田京介, 井之上直也. JAQKET: クイズを題材にした日本語QAデータセットの構築. 言語処理学会第26回年次大会論文集, 4 pages, March 2020.

45. 澤田 慎太郎, 中川 智皓, 新谷 篤彦, 井之上 直也. 対話的議論の自動評価に向けたディベートデータセットの構築. 言語処理学会第26回年次大会論文集, 4 pages, March 2020.

46. 谷口 忠大, 蓮 行, 中川 智皓, 石川 竜一郎, 井之上 直也, 益井 博史, 末長 英里子, コミュニケーション場のメカニズムデザインにおける設計変数の抽出と検討, 計測自動制御学会 システム・情報部門学術講演会2019（SSI2019）, 2019.

47. Naoya Inoue, Pontus Stenetorp, Kentaro Inui. A Crowdsourceable Protocol for Annotating Multi-Hop QA with Reasoning Steps. 言語処理学会第25回年次大会論文集, 4 pages, March 2019.

48. Qin Dai, Naoya Inoue, Paul Reisert, Kentaro Inui. End-to-End Scientific Knowledge Graph Completion via Word Embedding based Entity Type Classification. 言語処理学会第25回年次大会論文集, 4 pages, March 2019.

49. Paul Anthony Reisert, Naoya Inoue, Kentaro Inui. A Crowdsourceable Protocol for Collecting User-Generated Counter-Arguments. 言語処理学会第25回年次大会論文集, 4 pages, March 2019.

50. Pride Kavumba, Naoya Inoue, Kentaro Inui. Exploring Supervised Learning of Hierarchical Event Embedding with Poincaré Embeddings. 言語処理学会第25回年次大会論文集, 4 pages, March 2019.

51. 大竹孝樹, 横井祥, 井之上直也, 乾健太郎. 顕現的要素の出現順序に基づく物語の類似性尺度. 言語処理学会第25回年次大会論文集, 4 pages, March 2019.

52. 王天奇, 井之上直也, 水本智也, 大内啓樹, 乾健太郎. 採点基準を利用した記述式答案の自動採点. 言語処理学会第25回年次大会論文集, 4 pages, March 2019.

53. 佐藤志貴, 大内啓樹, 井之上直也, 鈴木潤, 乾健太郎. フレーズ単位の発話応答ペアを用いた対話応答生成の多様化. 言語処理学会第25回年次大会論文集, 4 pages, March 2019.

54. 栗林樹生, 大内啓樹, 井之上直也, Paul Reisert, 三好利昇, 鈴木潤, 乾健太郎. 複数の言語単位に対するスパン表現を用いた論述構造解析. 言語処理学会第25回年次大会論文集, 4 pages, March 2019.

55. 白井穂乃, 井之上直也, 鈴木潤, 乾健太郎. 計算機科学論文における手法の利点・欠点に着目したデータの構築と分析. 言語処理学会第25回年次大会論文集, 4 pages, March 2019.

56. Keshav Singh, Naoya Inoue, Paul Reisert, Kentaro Inui. Improving Evidence Detection using Warrants as External Knowledge. 言語処理学会第25回年次大会論文集, 4 pages, March 2019.

57. 内藤昭一, 井之上直也, 乾健太郎. クラウドソーシングによるパーラメンタリーディベートへの論述構造のアノテーション. 言語処理学会第25回年次大会論文集, 4 pages, March 2019.

58. Farjana Sultana Mim, Naoya Inoue, Paul Reisert, Hiroki Ouchi, Kentaro Inui. Unsupervised Learning of Discourse-Aware Text Representation. 言語処理学会第25回年次大会論文集, 4 pages, March 2019.

59. 阿部智彦, 井之上直也. 論述構造との同時予測による論述的な意見生成. 言語処理学会第25回年次大会論文集, 4 pages, March 2019.

60. 白井 穂乃, 井之上 直也, 乾健太郎. 情報科学論文からの技術の利点・欠点のマイニングに向けて. NLP若手の会 第13回シンポジウム, August 2018. (奨励賞)

61. Naoya Inoue, Paul Reisert, and Kentaro Inui. Exploring Crowdsourceable Annotation Protocol for Argumentation Schemes. In IPSJ SIG Technical Reports. Vol.2017-NL-236, pp.1-6, July 2018.

62. 白井 穂乃, 井之上 直也. 情報科学論文における問題解決手法と評価表現の付与仕様の検討. 人工知能学会全国大会 (第32回) 論文集, 4 pages, June 2018.

63. Naoya Inoue, Pontus Stenetorp, Sebastian Riedel, and Kentaro Inui. Towards Interpretation as Natural Logic Abduction. 人工知能学会全国大会 (第32回) 論文集, 4 pages, June 2018.

64. Tianqi Wang, Tomoya Mizumoto, Naoya Inoue, and Kentaro Inui. Identifying Current Issues in Short Answer Grading. 言語処理学会第24回年次大会論文集, pp.480-483, March 2018.

65. Tatsuki Kuribayashi, Paul Reisert, Naoya Inoue, and Kentaro Inui. Towards Exploiting Argumentative Context for Argumentative Relation Identification. 言語処理学会第24回年次大会論文集, pp.284-287, March 2018.

66. Tatsuki Kuribayashi, Paul Reisert, Naoya Inoue, and Kentaro Inui. Examining Macro-level Argumentative Structure Features for Argumentative Relation Identification. In IPSJ SIG Technical Reports. Vol.2017-NL-234, pp.1-5, December 2017.

67. 佐々木翔大, 高瀬翔, 井之上直也, 岡崎直観, 乾健太郎. 複単語表現を利用した因果関係推定モデルの改善. 情報処理学会研究報告. 自然言語処理研究会報告, Vol.2017-SLP-116 (22), pp.1-6, May 2017.

68. Paul Reisert, Naoya Inoue, Naoaki Okazaki, and Kentaro Inui. Deep Argumentative Structure Analysis as an Explanation to Argumentative Relations. 言語処理学会第23回年次大会論文集, pp.38-41, March 2017.

69. 佐々木翔大, 高瀬翔, 井之上直也, 岡崎直観, 乾健太郎. 分散表現を用いた因果関係のモデル化. NLP若手の会 第11回シンポジウム, August 2016.

70. 高橋諒, 井之上直也, 栗谷康隆, 山本風人, 乾健太郎. 交通オントロジと説明生成に基づく交通危険予測. 人工知能学会全国大会 (第30回) 論文集, June 2016.

71. 佐藤祥多, 井之上直也, 乾健太郎, 樋口佐和, 渡部生聖. 因果関係に基づく雑談対話発話生成の試み. 人工知能学会全国大会 (第30回) 論文集, June 2016.

72. 井之上直也, 岡崎直観, 乾健太郎. 感情状態に基づく因果関係推論の一般化. 言語処理学会第22回年次大会論文集, pp.889-892, March 2016. paper (draft) slides

73. 大野雅之, 井之上直也, 松林優一郎, 岡崎直観, 乾健太郎. 分散表現による文脈情報を用いた選択選好モデル. 言語処理学会第22回年次大会論文集, pp.885-888, March 2016. (最優秀賞)

74. 大野雅之, 井之上直也, 松林優一郎, 岡崎直観, 乾健太郎. 分散表現に基づく選択選好モデルの文脈化. 情報処理学会研究報告. 自然言語処理研究会報告, Vol.2016-NL-225, No.1, pp.1-9, January 2016. (優秀研究賞)

75. Paul Reisert, Naoya Inoue, Naoaki Okazaki, and Kentaro Inui. Determining Argument Strength and Consistency using a Causality-based Knowledge Graph. 第10回NLP若手の会 シンポジウム, September 2015.

76. 小林颯介,井之上直也,栗谷康隆,近藤敏之,安部克則,奥野英一,乾健太郎. 物理モデルと論理推論の統合による運転シーンの潜在的危険の予測. 自動車技術会 2015年春季大会学術講演会講演予稿集, pp.1076-1081, May 2015.

77. 山本風人, 井之上直也, 乾健太郎. 言語処理のための仮説推論エンジン Phillip. 言語処理学会第21回年次大会論文集, pp.377-380, March 2015.

78. Computationalizing a Toulmin Model for Argumentation Generation. Paul Reisert, Naoya Inoue, Kentaro Inui, Toshihiko Yanase, and Kohsuke Yanai. 言語処理学会第21回年次大会論文集, pp.828-831, March 2015.

79. 井之上直也, 杉浦純, Canasai Kruengkrai, 乾健太郎. 共参照解析のための事象間関係知識の一般化に向けて. NLP若手の会 第9回シンポジウム, September 2014. poster

80. 山本 風人,井之上 直也, 乾 健太郎, 荒瀬 由紀, 辻井 潤一. A*探索に基づく仮説推論の効率化. 情報処理学会研究報告, Vol.2014-NL-217, July 2014.

81. 井之上直也, 杉浦純, 乾健太郎. 共参照解析のための事象間関係知識の文脈化. 言語処理学会第20回年次大会論文集, pp.717-720, March 2014. paper (draft) slides (最優秀賞)

82. 杉浦純, 井之上直也, 乾健太郎. 共参照解析における事象間関係知識の適用. 言語処理学会第20回年次大会論文集, pp.713-716, March 2014.

83. 稲田和明, 松林優一郎, 井之上直也, 乾健太郎. 効率的な推論処理のための日本語文の論理式変換に向けて. 言語処理学会第18回年次大会論文集, March 2013.

84. Daiqin, Naoya Inoue, Kentaro Inui and Naoaki Okazaki. Acquisition of Inference Rules for Distinct Relative Entities. The 8th Symposium on Young Researcher Association for NLP Studies, September 2013.

85. Naoya Inoue, Kazeto Yamamoto, Yotaro Watanabe, Naoaki Okazaki, and Kentaro Inui. Online Large-margin Weight Learning for First-order Logic-based Abduction. In Proceedings of the 15th Information-Based Induction Sciences Workshop, pp.143-150, November 2012. paper (draft) poster (Honorable Mention)

86. Naoya Inoue and Kentaro Inui. Extending ILP-based Abductive Inference with Cutting Plane Inference. In IPSJ SIG Technical Reports, Vol. 2012-NL-208 (5), pp.1-8, September 2012. slides

87. 杉浦純, 井之上直也, 乾健太郎. 談話関係認識への連想情報の応用. NLP若手の会 第7回シンポジウム, September 2012.

88. 山本風人, 井之上直也, 渡邊陽太郎, 岡崎直観, 乾健太郎. 重み付き仮説推論における部分的な正解仮説からの識別学習. NLP若手の会 第7回シンポジウム, September 2012. (奨励賞)

89. 山本風人, 井之上直也, 渡邊陽太郎, 岡崎直観, 乾健太郎. 誤差逆伝播を利用した重み付き仮説推論の教師あり学習. 情報処理学会研究報告, Vol.2012-NL-206, May 2012. (学生奨励賞)

90. 井之上直也, 乾健太郎, Ekaterina Ovchinnikova, Jerry R. Hobbs. 大規模世界知識を用いた仮説推論による談話解析の課題と対策. 言語処理学会第18回年次大会論文集, pp.119-122, March 2012. paper (draft) slides (優秀賞)

91. 杉浦純, 井之上直也, 乾健太郎. 説明生成に基づく談話構造解析の課題分析. 言語処理学会第18回年次大会論文集, pp.115-118, March 2012.

92. Kentaro Inui and Naoya Inoue. Scalable Abduction for Deep NLP. Workshop ‘Perspectives on Processing Japanese’, October 2011.

93. 杉浦純, 井之上直也, 乾健太郎. 大規模語彙知識を用いた仮説推論による文章理解モデルの構築に向けて. NLP若手の会 第6回シンポジウム, September 2011. (優秀発表賞)

94. Naoya Inoue and Kentaro Inui. An ILP Formulation of Abductive Inference for Discourse Interpretation. In IPSJ SIG Technical Reports, Vol. 2011-NL-203 (3), pp.1-13, September 2011. slides (山下記念研究賞)

95. Naoya Inoue and Kentaro Inui. Toward Plan Recognition in Discourse Using Large-Scale Lexical Resources. 言語処理学会第17回年次大会発表論文集, pp. 928-931, March 2011. paper slides

96. 井之上直也, 乾健太郎. 文章に潜在する書き手の心的状態推定に向けて. 自然言語処理若手の会第5回シンポジウム, September 2010. poster

97. 井之上直也, 飯田龍, 乾健太郎, 松本裕治. 日本語文章における直接照応および間接照応の統合的解析. 情報処理学会第72回全国大会講演論文集, pp.2-541-542, March 2010. paper (draft)

98. 井之上直也, 飯田龍, 乾健太郎, 松本裕治. 指定指示・代行指示を区別した指示連体詞の照応解析. 言語処理学会第15回年次大会発表論文集, pp.372-375, March 2009. paper (draft) slides

99. 井之上直也, 江口萌, 有木隼人. wrica -ブログパーツで繋がる相互添削ネットワーク-. 自然言語処理学会若手の会第3回シンポジウム, September 2008. poster

Thesis

1. Naoya Inoue. Exploiting World Knowledge in Discourse Processing: A Comparison of Feature-Based and Inference-Based Approaches. Doctoral Dissertation, Tohoku University, March 2013. thesis

2. Naoya Inoue. Anaphora Resolution for Japanese Definite Noun Phrases. Master’s Thesis, Nara Institute of Science and Technology, March 2010. thesis

Invited Talks

1. Naoya Inoue. Panelist at LLMs and Linguistic Competence. LLMs and Philosophy. September 2024.

2. 井之上直也. 推論の上にも十五年. みちのく情報伝達学セミナー. March 2024.

3. 井之上直也. 大規模言語モデルは”考える”ことができるのか. JAIST産学官共創フォーラム 令和5年度 第3回定期講演会, January 2024. slides

4. Naoya Inoue. Towards Complex Reasoning with Large Language Models. JAIST Interpretable AI Center International Workshop on Interpretable AI, September 2023.

5. 井之上直也. 説明生成NLPの最前線 〜Lang&Roboとの接点を添えて〜. 第11回 Language and Robotics研究会, January 2023.

6. 井之上直也. パネリスト at パネルディスカッション「構造化知識を使った言語処理応用」. 森羅2022最終報告会, January 2023.

7. 井之上直也. 説明可能で合理的な推論ができる自然言語処理へのいざない. 名古屋地区NLPセミナー, December 2022.

8. Naoya Inoue. Beyond Performance Benchmarking: Towards Explainable and Rationalized NLP Systems. Advanced AI Autumn School at Thai Binh Duong University, October 2022. slides

9. 井之上直也. 知識に根ざした機械読解に向けて. 森羅2022 キックオフミーティング, May 2022.

10. 井之上直也. Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension 〜論文にまとめるまでの経緯を添えて〜. NLPコロキウム, May 2022.

11. 井之上直也. 自然言語処理システムは本当に言語を理解しているか？ 全脳アーキテクチャ若手の会 シンポジウム, March 2020.

12. 井之上直也. 議論を対象とした自然言語処理の最前線. 産業総合技術研究所 人工知能研究センター 第29回AIセミナー, December 2018.

13. 井之上直也. 計算機にも議論ができるか. 東北大学大学院情報科学研究科 第73回情報科学談話会, December 2018.

14. Naoya Inoue. Encoder-Decoder Abduction: Flexible Abductive Reasoning with Distributed Representations. 4th Seminar on Language and Robotics, January 2018.

15. 井之上直也, 山口 健史. 大規模言語資源を活用した自然言語処理. Gfarm シンポジウム2017, December 2017.

16. 井之上直也. 説明生成に基づく交通シーンの危険予測. 自動車技術会第14回エレクトロニクス部門委員会, February 2016.

Awards

1. 言語処理学会 第30回年次大会 優秀賞 (Annual Meeting Excellent Paper Award (second place) of the 30-th Annual Meeting of the Association for Natural Language Processing) (2024)

2. 言語処理学会 第30回年次大会 委員特別賞 (2024)

3. 言語処理学会 第30回年次大会 スポンサー賞 (SB Intuitions 株式会社) (2024)

4. JSAI Annual Conference Award 2023/人工知能学会全国大会優秀賞2023 (2023)

5. Advanced Robotics Best Survey Paper Award (2021)

6. 言語処理学会 2020年度最優秀論文賞 (Association for Natural Language Processing Best Paper Award 2020)

7. Annual Meeting Excellent Linguistic Resource Award of the 26-th annual meeting of the association for natural language processing (2020)

8. NLP 若手の会 第13回シンポジウム ハッカソン賞 (チーム受賞) (2018)

9. NLP 若手の会 第13回シンポジウム 奨励賞 (2018)

10. 船井情報科学振興財団 研究奨励賞 (2018)

11. トーキン科学技術賞 (2018)

12. Annual Meeting Excellent Paper Award (first place) of the 22-th annual meeting of the association for natural language processing (2016)

13. IPSJ SIG-NL Excellent Research Award (2015)

14. 言語処理学会 20周年記念論文賞 (2014)

15. Annual Meeting Excellent Paper Award (first place) of the 20-th annual meeting of the association for natural language processing (2014)

16. Dean’s Award for Excellence in Graduate School of Information Sciences at Tohoku University (2013)

17. IBIS2012 Honorable Mention (2012)

18. IPSJ Yamashita SIG Research Award (2012)

19. Annual Meeting Excellent Paper Award (second place) of the 18-th annual meeting of the association for natural language processing (2012)

20. IPSJ Certificate of excellent Master’s Thesis (2010)

Grants

• 井之上 直也 (PI). 人々が頼りたくなる自己批判的思考力を備えた言語処理機構. JST 2023年度 創発的研究支援事業, 2024/10-2028/03.

• 井之上 直也 (PI). 自己認識的に推論ができる信頼性の高いAIの研究. 中島国際交流財団 日本人独立研究者始動助成金, 2024/04-2027/03, 5,000,000JPY.

• 乾 健太郎, 井之上 直也, 中川 智皓, HEINZERLING BENJAMIN, 吉川 将司. 深い論述理解の計算モデリングと論述学習支援への応用. JSPS Grant-in-Aid for Scientific Research (KAKENHI 基盤A). 22H00524. 2022/04/01-2027/03/31, 41,470,000JPY.

• Naoya Inoue (PI). Developing Flexible Inference Mechanism by Embedding Causality Knowledge into Continuous Space (事象間関係知識の連続空間への埋め込みによる柔軟な推論機構の開発). JSPS Grants-in-Aid for Scientific Research (KAKENHI 若手研究). 19K20332. 2019/04-2020/3, 2022/04-2025/03, 4,160,000JPY.

• Naoya Inoue (PI). Integrating Structured Knowledge Base with Raw Corpora for Abductive Inference (構造化知識とテキスト上の知識の統合的埋め込みによる説明付き推論). 2019年度AIPチャレンジ. 2019/08-2020/03. 1,000,000JPY.

• Pontus Stenetorp, Kentaro Inui, and Naoya Inoue (collaborator). Creating Large-scale Corpus for Machine Reading Comprehension with Human Reasoning. UCL-Tohoku Strategic Partner Funds. 2019/06-2020/03. £10,000.

• Tadahiro Taniguchi, Chihiro Nakagawa, Naoya Inoue (Collaborator). Mechanism Design for Accelerating Circulation and Extension of Knowledge (「知」の循環と拡張を加速する対話空間のメカニズムデザイン). Japan Science and Technology Agency (JST) (JST未来社会創造事業（探索加速型）「持続可能な社会の実現」領域). 2017/04-2020/03. 60,000,000JPY.

• Naoya Inoue (PI). Creating Annotated Corpus of Argumentation Schemes (論述スキームのタグ付きコーパスの構築と自動推定手法の研究). 2018年度AIPチャレンジ. 2018/08-2019/03. 1,000,000JPY.

• Naoya Inoue (PI). Structuring and Aggregating Widely Spread Pieces of World Knowledge. Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research (KAKENHI 研究活動スタート支援). 16H06614. 2016/10-2018/03. 2,990,000JPY.

• Kentaro Inui, Naoaki Okazaki, Naoya Inoue (Collaborator). Reading between the Lines by Integrating Logical Inference, Machine Learning and Physics Simulation (論理推論・機械学習・物理計算の融合によって「行間を読む」談話解析モデル). Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research (KAKENHI 基盤研究 (A)). 15H01702. 2015/04-2019/03. 21,060,000JPY.

• Naoya Inoue (PI). Creating Dialogue Simulator and Its Application to Discourse Analysis (対話シミュレータの構築と談話分析への応用). Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research (JSPS 特別研究員奨励費 (DC1)). 10J09719. 2010/04-2012/03. 1,200,000JPY.

Patents

1. 対話処理装置. 乾健太郎, 井之上直也, 佐藤祥多, 渡部生聖, 樋口佐和. 特願2016-100653. 特開2017-207663.

2. 危険予測装置、運転支援システム. 井之上直也, 奥野英一, 安部克則, 近藤敏之, 栗谷康隆, 乾健太郎. 特願2014-220329, 特開2016-091039.

Media

1. 井之上直也. TohokuNLP MY DECISION. 2024/3 掲載. webpage

2. 井之上直也. JAIST 教員インタビュー（この人に聞く）, 2023/11 掲載. webpage

3. 井之上直也. 北陸放送 (MRO) Atta 特集「チャットGPT 期待と懸念は」, 2023/4/19 放送. webpage

Miscellaneous

1. Naoya Inoue. Large-scale Pretrained Language Models for Commonsense Reasoning? 6th Seminar on Language and Robotics, October 2019.

2. Naoya Inoue. Identifying Logical Structures in Argumentative Texts. JST-CREST International Symposium on Big Data Application, January 2018.

3. Paul Reisert, Naoya Inoue. Towards Capturing Implicit Reasoning of Argumentative Texts. Informal Workshop on Argument Mining, January 2018.

4. Naoya Inoue. An Encoder-Decoder Approach to Abductive Reasoning with Distributed Representations. 情報系 WINTER FESTA Episode3, December 2017.

5. 井之上直也, 乾健太郎. 書き手の問題解決プランの推定手法の検討. 自然言語処理合同研究会2010, November 2010. poster

6. NAIST Creative and International Competitiveness Project (CICP2008)“Dear Proofreader(拝啓 添削者様) - Construction of a correction network with blog plugin -“ poster presented in NAIST Science Festival 2009. poster