Abstract
This paper presents our Chinese-to-Japanese patent machine translation system for WAT 2016 (Group ID: ntt) that uses syntactic pre-ordering over Chinese dependency structures. Chinese words are reordered by a learning-to-rank model based on pairwise classification to obtain word order close to Japanese. In this year’s system, two different machine translation methods are compared: traditional phrase-based statistical machine translation and recent sequence-to-sequence neural machine translation with an attention mechanism. Our pre-ordering showed a significant improvement over the phrase-based baseline, but, in contrast, it degraded the neural machine translation baseline.- Anthology ID:
- W16-4621
- Volume:
- Proceedings of the 3rd Workshop on Asian Translation (WAT2016)
- Month:
- December
- Year:
- 2016
- Address:
- Osaka, Japan
- Editors:
- Toshiaki Nakazawa, Hideya Mino, Chenchen Ding, Isao Goto, Graham Neubig, Sadao Kurohashi, Ir. Hammam Riza, Pushpak Bhattacharyya
- Venue:
- WAT
- SIG:
- Publisher:
- The COLING 2016 Organizing Committee
- Note:
- Pages:
- 211–215
- Language:
- URL:
- https://aclanthology.org/W16-4621
- DOI:
- Cite (ACL):
- Katsuhito Sudoh and Masaaki Nagata. 2016. Chinese-to-Japanese Patent Machine Translation based on Syntactic Pre-ordering for WAT 2016. In Proceedings of the 3rd Workshop on Asian Translation (WAT2016), pages 211–215, Osaka, Japan. The COLING 2016 Organizing Committee.
- Cite (Informal):
- Chinese-to-Japanese Patent Machine Translation based on Syntactic Pre-ordering for WAT 2016 (Sudoh & Nagata, WAT 2016)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/W16-4621.pdf