Controlling Target Features in Neural Machine Translation via Prefix Constraints

Shunsuke Takeno, Masaaki Nagata, Kazuhide Yamamoto


Abstract
We propose prefix constraints, a novel method to enforce constraints on target sentences in neural machine translation. It places a sequence of special tokens at the beginning of target sentence (target prefix), while side constraints places a special token at the end of source sentence (source suffix). Prefix constraints can be predicted from source sentence jointly with target sentence, while side constraints (Sennrich et al., 2016) must be provided by the user or predicted by some other methods. In both methods, special tokens are designed to encode arbitrary features on target-side or metatextual information. We show that prefix constraints are more flexible than side constraints and can be used to control the behavior of neural machine translation, in terms of output length, bidirectional decoding, domain adaptation, and unaligned target word generation.
Anthology ID:
W17-5702
Volume:
Proceedings of the 4th Workshop on Asian Translation (WAT2017)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Toshiaki Nakazawa, Isao Goto
Venue:
WAT
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
55–63
Language:
URL:
https://aclanthology.org/W17-5702
DOI:
Bibkey:
Cite (ACL):
Shunsuke Takeno, Masaaki Nagata, and Kazuhide Yamamoto. 2017. Controlling Target Features in Neural Machine Translation via Prefix Constraints. In Proceedings of the 4th Workshop on Asian Translation (WAT2017), pages 55–63, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Controlling Target Features in Neural Machine Translation via Prefix Constraints (Takeno et al., WAT 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-5702.pdf