Hi, I am Keisuke Shirai, a researcher at Kyoto University. I received my PhD from Kyoto University, where I was supervised by Shinsuke Mori. My research interests include natural language understanding, language grounding, and multimodal learning.
Yuto Haneji, Taichi Nishimura, Hirotaka Kameko, Keisuke Shirai, Tomoya Yoshida, Keiya Kajimura, Koki Yamamoto, Taiyu Cui, Tomohiro Nishimoto, and Shinsuke Mori.
EgoOops: A Dataset for Mistake Action Detection from Egocentric Videos with Procedural Texts.
ArXiv. October 2024.
[Paper] [Dataset] [Project Website]
Keyaki Ohno, Hirotaka Kameko, Keisuke Shirai, Taichi Nishimura, and Shinsuke Mori.
Automatic Construction of a Large-Scale Corpus for Geoparsing Using Wikipedia Hyperlinks.
Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING). May 2024.
[Paper] [Code]
Keisuke Shirai, Cristian C. Beltran-Hernandez, Masashi Hamaya, Atsushi Hashimoto, Shohei Tanaka, Kento Kawaharazuka, Kazutoshi Tanaka, Yoshitaka Ushiku, and Shinsuke Mori.
Vision-Language Interpreter for Robot Task Planning.
International Conference on Robotics and Automation (ICRA). May 2024.
[Paper] [Code] [Project Website]
Keisuke Shirai, Hirotaka Kameko, and Shinsuke Mori.
Towards Flow Graph Prediction of Open-Domain Procedural Texts.
Workshop on Representation Learning for NLP (RepL4NLP). July 2023.
[Paper] [Dataset]
Keisuke Shirai, Atsushi Hashimoto, Taichi Nishimura, Hirotaka Kameko, Shuhei Kurita, Yoshitaka Ushiku, and Shinsuke Mori.
Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows.
International Conference on Computational Linguistics (COLING). October 2022.
[Paper] [Dataset] [Tool]
Kento Tanaka, Taichi Nishimura, Hiroaki Nanjo, Keisuke Shirai, Hirotaka Kameko, and Masatake Dantsuji.
Image Description Dataset for Language Learners.
Language Resources and Evaluation Conference (LREC). June 2022.
[Paper]
Keisuke Shirai, Kazuma Hashimoto, Akiko Eriguchi, Takashi Ninomiya, and Shinsuke Mori.
Neural Text Generation with Artificial Negative Examples.
ArXiv. December 2020.
[Paper]
Keisuke Shirai, Hirotaka Kameko, and Shinsuke Mori.
Flow Graph Prediction of Open-Domain Procedural Texts (in Japanese).
Journal of Natural Language Processing. June 2024.
Keisuke Shirai, Atsushi Hashimoto, Taichi Nishimura, Hirotaka Kameko, Shuhei Kurita, and Shinsuke Mori.
Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows (in Japanese).
Journal of Natural Language Processing. September 2023.
[Paper]
Keisuke Shirai, Masato Matsuzaki, Shinsuke Mori, and Makoto Goto.
Knowledge Extraction from a Biographical Dictionary (in Japanese).
IPSJ Journal. February 2022.
[Paper]
Keisuke Shirai, Kazuma Hashimoto, Akiko Eriguchi, Takashi Ninomiya, and Shinsuke Mori.
Neural Text Generation with Artificial Negative Examples to Address Repeating and Dropping Errors.
Journal of Natural Language Processing. September 2021.
[Paper]
Shoichiro Hara, Taizo Yamada, Masatoshi Ishikawa, Keisuke Shirai, Akihiro Kameda, and Shinsuke Mori.
Prototyping Information System to Extract Area Study Information from Web Big Data.
International Journal of Geoinformatics. June 2019.
| Apr 2023 - Mar 2024 | Research Intern, OMRON SINIC X |
| Mar 2021 - May 2021 | Research Intern, rinna Co., Ltd. |
| Jul 2018 - Jul 2018 | Intern, Japan Aerospace Exploration Agency |
| Aug 2017 - Sep 2017 | Intern, Recruit Holdings |