石垣達也's page

論文

国際会議 (査読あり)

1. Perspective-Diverse Utterance Candidate Generation via Input Variation for Race Game Commentary, Mizuki Arai, Tatsuya Ishigaki, Yusuke Miyao, Hiroya Takamura, Ichiro Kobayashi, INLG2026 (Main conference)

2. Mid-Utterance Transition Control for Audio Commentary Generation, Ryota Kawamatsu, Tatsuya Ishigaki, Hiroya Takamura, INLG2026 (Main conference)

3. BikeCoach: A Demo System for Aspect-based Advice Generation Conditioned on Sport Training Protocols, Matīss Rikters, Tatsuya Ishigaki, Masayuki Kawarada, Shota Kato, Sohei Washino, Hiroki Yamaguchi, INLG2026 (demo track)

4. Low-Latency Real-Time Audio Game Commentary System via LLM-based Parallel Text Generation, Ryota Kawamatsu, Anum Afzal, Yuki Saito, Shinnosuke Takamichi, Graham Neubig, Katsuhito Sudoh, Hiroya Takamura, Tatsuya Ishigaki, IJCAI-ECAI2026 (demo track)

5. Aggregate vs. Personalized Judges in Business Idea Evaluation: Evidence from Expert Disagreement, Wataru Hirota, Tomoki Taniguchi, Tomoko Ohkuma, Kosuke Takahashi, Takahiro Omi, Kosuke Arima, Takuto Asakura, Chung-Chi Chen, Tatsuya Ishigaki, ACL2026 (Industry Track)

6. Assessing the Belief Consistency of Large Language Models on the Logical Conversation Process, Tomoki Tsujimura, Matīss Rikters, Masaki Asada, Shusaku Egami, Tatsuya Ishigaki, Ken Yano, Hiroya Takamura, ACL2026 (SAC Highlihgt Award)

7. Citation-Aware Continual Pre-Training for Biomedical Language Models, Masaki Asada, Tomoki Tsujimura, Tatsuya Ishigaki, Shusaku Egami, Ken Fukuda, Hiroya Takamura, BioNLP2026

8. A Model Context Protocol Server for Quantum Execution in Hybrid Quantum-HPC Environments, Masaki Shiraishi, Ikko Hamamura, Tatsuya Ishigaki and Tadashi Kadowaki, QCNC2026 (accepted to refereed workshop)

9. Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches, Anum Afzal, Hiroya Takamura, Katsuhito Sudoh, Yuki Saito, Shinnosuke Takamichi, Graham Neubig, Florian Matthes and Tatsuya Ishigaki, LREC2026

10. Multimodal Task Interference: A Benchmark and Analysis of History-Target Mismatch in Multimodal LLMs, Masayuki Kawarada, Tatsuya Ishigaki and Hiroya Takamura, LREC2026

11. HOME-KGQA: A Benchmark Dataset for Multimodal Knowledge Graph Question Answering on Household Daily Activities, Shusaku Egami, Aoi Ohta, Tomoki Tsujimura, Masaki Asada, Tatsuya Ishigaki, Ken Fukuda, Masahiro Hamasaki and Hiroya Takamura, LREC2026

12. Evaluating Social Intelligence in LLMs via Japanese Honorifics in Business Emails: A Social Semiotic System Perspective, Muxuan Liu, Tatsuya Ishigaki, Yusuke Miyao, Hiroya Takamura and Ichiro Kobayashi, LREC2026

13. A Comparative Study of Demonstration Selection for Practical Large Language Models-based Next POI Prediction, Ryo Nishida, Masayuki Kawarada, Tatsuya Ishigaki, Hiroya Takamura and Masaki Onishi, PRICAI2025

14. VitaEval: Open-source Human Evaluation Tool for Video-to-Text and Video-to-Audio Systems, Goran Topic, Yuki Saito, Katsuhito Sudoh, Shinnosuke Takamichi, Hiroya Takamura, Graham Neubig and Tatsuya Ishigaki, INLG2025 (demo track)

15. QCoder Benchmark: Bridging Language Generation and Quantum Hardware through Simulator-Based Feedback, Taku Mikuriya, Tatsuya Ishigaki, Shunya Minami, Tadashi Kadowaki, Yohichi Suzuki, Shun Naito, Shunya Takada, Takumi Kato, Tamotsu Baseda, Reo Yamada and Hiroya Takamura, INLG2025

16. Evaluating LLMs' Ability to Understand Numerical Time Series for Text Generation, Mizuki Arai, Tatsuya Ishigaki, Masayuki Kawarada, Yusuke Miyao, Hiroya Takamura and Ichiro Kobayashi, INLG2025

17. Live Football Commentary (LFC): A Large‑Scale Dataset for Building Football Commentary Generation Models, Taiga Someya, Tatsuya Ishigaki and Hiroya Takamura, INLG2025

18. Measuring Time Delay Tolerance in Third-Person Live Commentary for Game Recordings, Ryosuke Matsushita, Ryosuke Sakai, Koki Fukuda, Shinnosuke Takamichi, Kota Iura, Yuki Saito, Graham Neubig, Katsuhito Sudoh, Hiroya Takamura, Tatsuya Ishigaki, IEEE Conference on Games (CoG2025)

19. Exploring the Design of Multi-Agent LLM Dialogues for Research Ideation, Keisuke Ueda, Wataru Hirota, Kosuke Takahashi, Takahiro Omi, Kosuke Arima and Tatsuya Ishigaki, SIGDIAL2025

20. Live Football Commentary System Providing Background Information, Yuichiro Mori, Chikara Tanaka, Aru Maekawa, Satoshi Kosugi, Tatsuya Ishigaki, Kotaro Funakoshi, Hiroya Takamura, Manabu Okumura,  ACL2025 (demo track)

21. Evaluating Llama-2's Adaptation to Social Context in Japanese Emails via Fine-Tuning, Muxuan Liu, Tatsuya Ishigaki, Yusuke Miyao, Hiroya Takamura, Ichiro Kobayashi, PACLIC2024

22. Pretraining and Updates of Domain-Specific LLM: A Case Study in the Japanese Business Domain, Kosuke Takahashi, Takahiro Omi, Kosuke Arima, Tatsuya Ishigaki, PACLIC2024

23. Demonstration Selection Strategies for Numerical Time Series Data-to-Text, Masayuki Kawarada, Tatsuya Ishigaki, Goran Topić, Hiroya Takamura, EMNLP2024 (Findings) [PDF]

24. Prompting for Numerical Sequences: A Case Study in Market Comment Generation, Masayuki Kawarada, Tatsuya Ishigaki, Hiroya Takamura, LREC-COLING2024

25. Training Generative Question-Answering on Synthetic Data Obtained from an Instruct-tuned Model, Kosuke Takahashi, Takahiro Omi, Kosuke Arima and Tatsuya Ishigaki, PACLIC2023

26. Constructing a Japanese Business Email Corpus Based on Social Situations, Muxuan Liu, Tatsuya Ishigaki, Yusuke Miyao, Hiroya Takamura and Ichiro Kobayashi, PACLIC2023

27. Audio Commentary System for Real-Time Racing Game Play, Tatsuya Ishigaki, Goran Topić, Yumi Hamazono, Ichiro Kobayashi, Yusuke Miyao and Hiroya Takamura, INLG2023 (demo paper, best paper award)

28. Pretraining Language- and Domain-Specific BERT on Automatically Translated Text, Tatsuya Ishigaki, Yui Uehara, Goran Topic, Hiroya Takamura, RANLP2023

29. Validation of a Foresight Support System to Imagine an Uncertain Future:-Effectiveness Testing through Scenario Planning Workshops, Suzuko Nishino, Yuichi Washida, Tatsuya Ishigaki, Sohei Washino, Hiroki IGARASHI, Akihiko Murai, Yukari Nagai, KICSS2023

30. Open-Domain Video Commentary Generation, Edison Marrese-Taylor, Yumi Hamazono, Tatsuya Ishigaki, Goran Topic, Yusuke Miyao, Ichiro Kobayashi, Hiroya Takamura, EMNLP2022 [paper]

31. Automating Horizon Scanning in Future Studies, Tatsuya Ishigaki, Suzuko Nishino, Sohei Washino, Hiroki Igarashi, Yukari Nagai, Yuichi Washida and Akihiko Murai, LREC2022 [paper]

32. Unpredictable Attributes in Data-to-text Generation, Yumi Hamazono, Tatsuya Ishigaki, Ichiro Kobayashi, Yusuke Miyao and Hiroya Takamura, PACLIC2021 (acceptance rate (oral): 48%=52/110)

33. Generating Racing Game Commentary from Vision, Language, and Structured Data, Tatsuya Ishigaki, Goran Topic, Yumi Hamazono, Hiroshi Noji, Ichiro Kobayashi, Yusuke Miyao and Hiroya Takamura, INLG2021 [paper] (acceptance rate: 40% = 31/76)

34. Learning with Contrastive Examples for Data-to-Text Generation, Yui Uehara*, Tatsuya Ishigaki* (*equal contribution), Kasumi Aoki, Hiroshi Noji, Keiichi Goshima, Ichiro Kobayashi, Hiroya Takamura and Yusuke Miyao, COLING2020 (acceptance rate: 32.9% = 644/1956)

35. Neural Query-biased Abstractive Summarization Using Copying Mechanism, Tatsuya Ishigaki, Hen-Hsen Huang, Hiroya Takamura, Hsin-Hsi Chen, Manabu Okumura, ECIR2020 [paper][video] (acceptance rate: 30% = 46/159)

36. Distant Supervision for Extractive Question Summarization, Tatsuya Ishigaki, Kazuya Machida, Hayato Kobayashi, Hiroya Takamura, Manabu Okumura, ECIR2020 [paper][video] (acceptance rate: 30% = 46/159)

37. Semi-Supervised Extractive Question Summarization Using Question-Answer Pairs, *Kazuya Machida, *Tatsuya Ishigaki (*equal contribution), Hayato Kobayashi, Hiroya Takamura, Manabu Okumura, ECIR2020 [paper][video]. (acceptance rate: 30% = 46/159)

38. Controlling Contents in Data-to-Document Generation with Human-Designed Topic Labels, Kasumi Aoki, Akira Miyazawa, Tatsuya Ishigaki, Tatsuya Aoki, Hiroshi Noji, Keiichi Goshima, Ichiro Kobayashi, Hiroya Takamura and Yusuke Miyao, INLG2019 [paper] (acceptance rate: 24.5% = 36/147)

39. Discourse-Aware Hierarchical Attention Network for Extractive Single-Document Summarization, Tatsuya Ishigaki, Hidetaka Kamigaito, Hiroya Takamura and Manabu Okumura, RANLP2019 [paper] (acceptance rate: 26.7% = 37/134)

40. Learning to Select, Track, and Generate for Data-to-Text, Hayate Iso, Yui Uehara, Tatsuya Ishigaki, Hiroshi Noji, Eiji Aramaki, Ichiro Kobayashi, Yusuke Miyao, Naoaki Okazaki, Hiroya Takamura, ACL2019 [paper] (acceptance rate 25.7% = 447/1740)

41. Generating Market Comments Referring to External Resources, Tatsuya Aoki, Akira Miyazawa, Kasumi Aoki, Keiichi Goshima, Tatsuya Ishigaki, Ichiro Kobayashi, Hiroya Takamura and Yusuke Miyao, INLG2018 [paper] (acceptance rate: 60% = 62/102)

42. Summarizing Lengthy Questions, Tatsuya Ishigaki, Hiroya Takamura, and Manabu Okumura, IJCNLP2017  [paper] (acceptance rate: 31% = 103/337)

論文誌

1. Large Language Models Predict Transportation Mode Choice Behavior for a Variety of Alternative Sets, Ryo Nishida, Tatsuya Ishigaki, Masaki Onishi, Transportation Research Record, 2025

2. ホライゾン・スキャニングの自動化のための言語処理応用, 西野 涼子，石垣 達也，鷲野 壮平，五十嵐 広希，村井 昭彦，鷲田 祐一，永井 由佳里, 自然言語処理 Vol.30 No.3, 2023

3. Controlling Contents in Data-to-Document Generation with Human-Designed Topic Labels, Kasumi Aoki, Akira Miyazawa, Tatsuya Ishigaki, Tatsuya Aoki, Hiroshi Noji, Keiichi Goshima, Ichiro Kobayashi, Hiroya Takamura and Yusuke Miyao, Computer Speech and Language Vol.66, 2020 [paper]

4. 質問−回答ペアを活用する半教師あり抽出型質問要約モデルとその学習法 , 石垣 達也，町田 和哉, 小林 隼人, 高村 大也，奥村 学, 自然言語処理 Vol.27 No.4 (2020年12月号), 2020

5. Learning to Select, Track, and Generate for Data-to-Text, Hayate Iso, Yui Uehara, Tatsuya Ishigaki, Hiroshi Noji, Eiji Aramaki, Ichiro Kobayashi, Yusuke Miyao, Naoaki Okazaki and Hiroya Takamura, 自然言語処理 Vol.27 No.3, 2020 [paper]

6. 複数文質問を対象とした抽出型および生成型要約, 石垣 達也，高村 大也，奥村 学, 自然言語処理 Volume 26 No.1 (2019年3月号),  2019 [paper]

学歴

• 博士 (工学)
  「ニューラルネットワークを用いた単一文書要約に関する研究」(2015年4月-2019年9月)
  東京工業大学大学院総合理工学研究科知能システム科学専攻
  指導教員: 教授 高村大也

• 修士 (工学)
  「対話形式を用いた分かりやすい情報提示」(2013年4月-2015年3月)
  東京工業大学大学院総合理工学研究科知能システム科学専攻
  指導教員: 教授 高村大也

• 訪問研究学生
  プロジェクト「超高度高齢社会のための情報想起支援システム」(2018年8月-2018年12月)
  国立台湾大学
  指導教員: 教授 Hsin-Hsi Chen

職歴

• サイバーエージェント Sports AI Tech Lab (2026年8月-現在): リサーチサイエンティスト

• 産総研 人工知能研究センター@産業技術総合研究所臨海副都心センター (2026年8月 -現在) : 客員研究員

• 産総研 人工知能研究センター@産業技術総合研究所臨海副都心センター (2025年10月 -2026年7月) : 主任研究員

• 産総研 人工知能研究センター@産業技術総合研究所臨海副都心センター (2020年12月 -2025年10月) : 研究員

• 産総研 人工知能研究センター@産業技術総合研究所臨海副都心センター (2020年4月-2020年10月): ポスドク

• 奥村研究室@東京工業大学未来産業技術研究所 (2019年4月- 2020年3月): ポスドク

• 人工知能研究センター@産業技術総合研究所臨海副都心センター  (2018年4月- 2019年3月) : テクニカルスタッフ

• 奥村研究室@東京工業大学未来産業技術研究所 (2018年4月- 2019年3月): RA

• 茨城工業高等専門学校 (2015年4月 - 2016年3月): 非常勤講師

その他

受賞

• SAC Highlight Award, ACL2026

• 優秀研究賞: 情報処理学会第240回自然言語処理研究会(NL250), 2021

• 優秀研究賞: 情報処理学会第240回自然言語処理研究会(NL240), 2019

• 若手奨励賞: 言語処理学会第25回年次大会(NLP2019), 2019

趣味

• 中日ドラゴンズ

• ワイナリー、醸造所、蒸溜所訪問

• ロードバイク