Chunk-based Decoder for Neural Machine Translation

Shonosuke Ishiwatari, Jingtao Yao, Shujie Liu, Mu Li, Ming Zhou, Naoki Yoshinaga, Masaru Kitsuregawa, Weijia Jia


Abstract
Chunks (or phrases) once played a pivotal role in machine translation. By using a chunk rather than a word as the basic translation unit, local (intra-chunk) and global (inter-chunk) word orders and dependencies can be easily modeled. The chunk structure, despite its importance, has not been considered in the decoders used for neural machine translation (NMT). In this paper, we propose chunk-based decoders for (NMT), each of which consists of a chunk-level decoder and a word-level decoder. The chunk-level decoder models global dependencies while the word-level decoder decides the local word order in a chunk. To output a target sentence, the chunk-level decoder generates a chunk representation containing global information, which the word-level decoder then uses as a basis to predict the words inside the chunk. Experimental results show that our proposed decoders can significantly improve translation performance in a WAT ‘16 English-to-Japanese translation task.
Anthology ID:
P17-1174
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1901–1912
Language:
URL:
https://aclanthology.org/P17-1174
DOI:
10.18653/v1/P17-1174
Bibkey:
Cite (ACL):
Shonosuke Ishiwatari, Jingtao Yao, Shujie Liu, Mu Li, Ming Zhou, Naoki Yoshinaga, Masaru Kitsuregawa, and Weijia Jia. 2017. Chunk-based Decoder for Neural Machine Translation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1901–1912, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Chunk-based Decoder for Neural Machine Translation (Ishiwatari et al., ACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/P17-1174.pdf
Data
ASPEC