企業との共同研究活動の一環として発表した成果の一覧です。（発表済みの案件のみ掲載）
This is a list of research outcomes published as part of our collaborative research activities with industry partners. (Only completed and publicly released projects are included.)
Predicting Fine-tuned Performance on Larger Datasets Before Creating Them.[paper]
Toshiki Kuramoto, Jun Suzuki.
In Proceedings of the 31st International Conference on Computational Linguistics(COLING 2025), pp.204-212,January 2025.
VDocRAG:Retrieval-Augmented Generation over Visually-Rich Documents.[paper]
Ryota Tanaka, Taichi Iki, Taku Hasegawa, Kyosuke Nishida, Kuniko Saito, Jun Suzuki.
In The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025(CVPR2025), pp.- ,Jun 2025.
Towards Automated Document Revision: Grammatical Error Correction.[paper]
Masato Mita, Keisuke Sakaguchi, Masato Hagiwara, Tomoya Mizumoto, Jun Suzuki, Kentaro Inui.
Fluency Edits, and Beyond. In Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 19), pp.251-265,June 2024.
A Challenging Multimodal Video Summary: Simultaneously Extracting and Generating Keyframe-Caption Pairs from Video.[paper]
Keito Kudo, Haruki Nagasawa, Jun Suzuki, Nobuyuki Shimizu.
In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023). pp.7380-7402,December 2023.