Abstract
This paper describes our MT systems’ participation in the of WAT 2019. We participated in the (i) Patent, (ii) Timely Disclosure, (iii) Newswire and (iv) Mixed-domain tasks. Our main focus is to explore how similar Transformer models perform on various tasks. We observed that for tasks with smaller datasets, our best model setup are shallower models with lesser number of attention heads. We investigated practical issues in NMT that often appear in production settings, such as coping with multilinguality and simplifying pre- and post-processing pipeline in deployment.- Anthology ID:
- D19-5219
- Volume:
- Proceedings of the 6th Workshop on Asian Translation
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- Toshiaki Nakazawa, Chenchen Ding, Raj Dabre, Anoop Kunchukuttan, Nobushige Doi, Yusuke Oda, Ondřej Bojar, Shantipriya Parida, Isao Goto, Hidaya Mino
- Venue:
- WAT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 152–158
- Language:
- URL:
- https://aclanthology.org/D19-5219
- DOI:
- 10.18653/v1/D19-5219
- Cite (ACL):
- Raymond Hendy Susanto, Ohnmar Htun, and Liling Tan. 2019. Sarah’s Participation in WAT 2019. In Proceedings of the 6th Workshop on Asian Translation, pages 152–158, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Sarah’s Participation in WAT 2019 (Susanto et al., WAT 2019)
- PDF:
- https://preview.aclanthology.org/landing_page/D19-5219.pdf