Abstract
In this paper, we describe our participation in the 2021 Workshop on Asian Translation (team ID: tpt_wat). We submitted results for all six directions of the JPC2 patent task. As a first-time participant in the task, we attempted to identify a single configuration that provided the best overall results across all language pairs. All our submissions were created using single base transformer models, trained on only the task-specific data, using a consistent configuration of hyperparameters. In contrast to the uniformity of our methods, our results vary widely across the six language pairs.- Anthology ID:
- 2021.wat-1.14
- Volume:
- Proceedings of the 8th Workshop on Asian Translation (WAT2021)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Toshiaki Nakazawa, Hideki Nakayama, Isao Goto, Hideya Mino, Chenchen Ding, Raj Dabre, Anoop Kunchukuttan, Shohei Higashiyama, Hiroshi Manabe, Win Pa Pa, Shantipriya Parida, Ondřej Bojar, Chenhui Chu, Akiko Eriguchi, Kaori Abe, Yusuke Oda, Katsuhito Sudoh, Sadao Kurohashi, Pushpak Bhattacharyya
- Venue:
- WAT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 138–140
- Language:
- URL:
- https://aclanthology.org/2021.wat-1.14
- DOI:
- 10.18653/v1/2021.wat-1.14
- Cite (ACL):
- Wiktor Stribiżew, Fred Bane, José Conceição, and Anna Zaretskaya. 2021. System Description for Transperfect. In Proceedings of the 8th Workshop on Asian Translation (WAT2021), pages 138–140, Online. Association for Computational Linguistics.
- Cite (Informal):
- System Description for Transperfect (Stribiżew et al., WAT 2021)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2021.wat-1.14.pdf