Preprints

1. Yukiya Hono, Koh Mitsuda, Tianyu Zhao, Kentaro Mitsui, Toshiaki Wakatsuki, Kei Sawada, An Integration of Pre-Trained Speech and Language Models for End-to-End Speech Recognition, arXiv, 2312.03668, 2023. [pdf] [github]

International Conference (Peer-Reviewed)

1. Kei Sawada, Tianyu Zhao, Makoto Shing, Kentaro Mitsui, Akio Kaga, Yukiya Hono, Toshiaki Wakatsuki, Koh Mitsuda, Release of Pre-Trained Models for the Japanese Language, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-Coling 2024), pp. XXX- XXX, 2024. [arxiv] [huggingface] (to be appeared)

2. Yuya Chiba, Koh Mitsuda, Akinobu Lee, Ryuichiro Higashinaka, The Remdis Toolkit: Building Advanced Real-time Multimodal Dialogue Systems with Incremental Processing and Large Language Models, Proceedings of the 14th International Workshop on Spoken Dialogue Systems Technology (IWSDS2024), pp. 1-6, 2024. [pdf] [poster] [github]

3. Yu Saito, Koh Mitsuda, Ryuichiro Higashinaka, Yasuhiro Minami, Investigation of Naming in Process of Building Common Ground through Collaborative Dialogue, Proceedings of the 13th International Workshop on Spoken Dialogue Systems Technology (IWSDS2023), pp. 1-13, 2023. [pdf] [poster]

4. Koh Mitsuda, Ryuichiro Higashinaka, Kuniko Saito, Combining Argumentation Structure and Language Model for Generating Natural Argumentative Dialogue, Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (AACL-IJCNLP2022), pp. 65-71, 2022. [pdf] [slide] [movie] (acceptance rate: 27%)

5. Koh Mitsuda, Ryuichiro Higashinaka, Yuhei Oga, Sen Yoshida, Dialogue Collection for Recording the Process of Building Common Ground in a Collaborative Task, Proceedings of the 13th Language Resources and Evaluation Conference (LREC2022), pp. 5749-5758, 2022. [pdf] [slide] [movie] (acceptance rate: 62%)

6. Yuki Furuya, Koki Saito, Kosuke Ogura, Koh Mitsuda, Ryuichiro Higashinaka, Kazunori Takashio, Dialogue Corpus Construction Considering Modality and Social Relationships in Building Common Ground, Proceedings of the 13th Language Resources and Evaluation Conference (LREC2022), pp. 4088-4095, 2022. [pdf]

7. Saki Sudo, Kyoshiro Asano, Koh Mitsuda, Ryuichiro Higashinaka, Yugo Takeuchi, A Speculative and Tentative Common Ground Handling for Efficient Composition of Uncertain Dialogue, Proceedings of the 13th Language Resources and Evaluation Conference (LREC2022), pp. 3150-3157, 2022. [pdf]

8. Koh Mitsuda, Ryuichiro Higashinaka, Tingxuan Li, and Sen Yoshida, Investigating person-specific errors in chat-oriented dialogue systems, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL2022), pp. 464-469, 2022. [pdf] [slide] [poster] [movie] (acceptance rate: 25%)

9. Koh Mitsuda, Ryuichiro Higashinaka, Hiroaki Sugiyama, Masahiro Mizukami, Tetsuya Kinebuchi, Ryuta Nakamura, Noritake Adachi, and Hidetoshi Kawabata, Fine-tuning a pre-trained Transformer-based encoder-decoder model with user-generated question-answer pairs to realize character-like chatbots, Proceedings of the 12th International Workshop on Spoken Dialog Systems (IWSDS2021), pp. 1-14, 2021. [pdf] [slide] [movie]

10. Takashi Kodama, Ryuichiro Higashinaka, Koh Mitsuda, Ryo Masumura, Yushi Aono, Ryuta Nakamura, Noritake Adachi, and Hidetoshi Kawabata, Generating Responses that Reflect Meta Information in User-Generated Question Answer Pairs, Proceedings of the 12th Language Resources and Evaluation Conference (LREC2020), pp. 5433-5441, 2020. [pdf]

11. Ryo Ishii, Ryuichiro Higashinaka, Koh Mitsuda, Taichi Katayama, Masahiro Mizukami, Junji Tomita, Hidetoshi Kawabata, Emi Yamaguchi, Noritake Adachi, and Yushi Aono, Methods of Efficiently Constructing Text-Dialogue-Agent System Using Existing Anime Character, Proceedings of HCI International 2020 (HCI2020), pp. 328-347, 2020. [pdf]

12. Koh Mitsuda, Ryuichiro Higashinaka, Taichi Katayama, and Junji Tomita, Generating supportive utterances for open-domain argumentative dialogue systems, Proceedings of the 10th International Workshop on Spoken Dialog Systems (IWSDS2019), pp. 1-12, 2019. [pdf] [slide]

13. Koh Mitsuda, Ryuichiro Higashinaka, and Junji Tomita, Investigating the effect of conveying understanding results in chat-oriented dialogue systems, Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP2017), pp. 389-394, 2017. [pdf] [slide] (acceptance rate: 31%)

14. Koh Mitsuda, Ryuichiro Higashinaka, and Yoshihiro Matsuo, What information should a dialogue system understand?: Collection and analysis of perceived information in chat-oriented dialogue, Proceedings of the 8th International Workshop on Spoken Dialog Systems (IWSDS2017), pp. 1-9, 2017. [pdf] [slide]

15. Koh Mitsuda, Ryu Iida, and Takenobu Tokunaga, Detecting Missing Annotation Disagreement using Eye Gaze Information, Proceedings of the 11th Workshop on Asian Language Resources (ALR-11), pp. 19-26, 2013. [pdf] [slide]

16. Ryu Iida, Koh Mitsuda, and Takenobu Tokunaga, Investigation of annotator's behaviour using eye-tracking data, Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse (LAW-7), pp. 214-222, 2013. [pdf]

17. Takenobu Tokunaga, Ryu Iida, and Koh Mitsuda, Annotation for annotation - Toward eliciting implicit linguistic knowledge through annotation -, Proceedings of the 9th Joint ISO - ACL SIGSEM Workshop on Interoperable Semantic Annotation (ISA-9), pp 79-83, 2013. [pdf]

Journal Article

1. Ryo Ishii, Ryuichiro Higashinaka, Koh Mitsuda, Taichi Katayama, Masahiro Mizukami, Junji Tomita, Hidetoshi Kawabata, Emi Yamaguchi, Noritake Adachi, Yushi Aono, Methods of Efficiently Constructing Text-dialogue-agent System using Existing Anime Character,  Journal of Information Processing, Vol. 29, pp. 30-44, 2021