Abstract
The paper describes the development process of the The University of Tokyo’s NMT systems that were submitted to the WAT 2020 Document-level Business Scene Dialogue Translation sub-task. We describe the data processing workflow, NMT system training architectures, and automatic evaluation results. For the WAT 2020 shared task, we submitted 12 systems (both constrained and unconstrained) for English-Japanese and Japanese-English translation directions. The submitted systems were trained using Transformer models and one was a SMT baseline.- Anthology ID:
- 2020.wat-1.18
- Volume:
- Proceedings of the 7th Workshop on Asian Translation
- Month:
- December
- Year:
- 2020
- Address:
- Suzhou, China
- Editors:
- Toshiaki Nakazawa, Hideki Nakayama, Chenchen Ding, Raj Dabre, Anoop Kunchukuttan, Win Pa Pa, Ondřej Bojar, Shantipriya Parida, Isao Goto, Hidaya Mino, Hiroshi Manabe, Katsuhito Sudoh, Sadao Kurohashi, Pushpak Bhattacharyya
- Venue:
- WAT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 147–153
- Language:
- URL:
- https://aclanthology.org/2020.wat-1.18
- DOI:
- Cite (ACL):
- Matīss Rikters, Toshiaki Nakazawa, and Ryokan Ri. 2020. The University of Tokyo’s Submissions to the WAT 2020 Shared Task. In Proceedings of the 7th Workshop on Asian Translation, pages 147–153, Suzhou, China. Association for Computational Linguistics.
- Cite (Informal):
- The University of Tokyo’s Submissions to the WAT 2020 Shared Task (Rikters et al., WAT 2020)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2020.wat-1.18.pdf
- Data
- Business Scene Dialogue, JESC, JParaCrawl