Phrase-based Machine Translation using Multiple Preordering Candidates

Yusuke Oda, Taku Kudo, Tetsuji Nakagawa, Taro Watanabe


Abstract
In this paper, we propose a new decoding method for phrase-based statistical machine translation which directly uses multiple preordering candidates as a graph structure. Compared with previous phrase-based decoding methods, our method is based on a simple left-to-right dynamic programming in which no decoding-time reordering is performed. As a result, its runtime is very fast and implementing the algorithm becomes easy. Our system does not depend on specific preordering methods as long as they output multiple preordering candidates, and it is trivial to employ existing preordering methods into our system. In our experiments for translating diverse 11 languages into English, the proposed method outperforms conventional phrase-based decoder in terms of translation qualities under comparable or faster decoding time.
Anthology ID:
C16-1134
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Yuji Matsumoto, Rashmi Prasad
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
1419–1428
Language:
URL:
https://aclanthology.org/C16-1134
DOI:
Bibkey:
Cite (ACL):
Yusuke Oda, Taku Kudo, Tetsuji Nakagawa, and Taro Watanabe. 2016. Phrase-based Machine Translation using Multiple Preordering Candidates. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1419–1428, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Phrase-based Machine Translation using Multiple Preordering Candidates (Oda et al., COLING 2016)
Copy Citation:
PDF:
https://aclanthology.org/C16-1134.pdf