Neural Machine Translation with Source Dependency Representation

Kehai Chen, Rui Wang, Masao Utiyama, Lemao Liu, Akihiro Tamura, Eiichiro Sumita, Tiejun Zhao


Abstract
Source dependency information has been successfully introduced into statistical machine translation. However, there are only a few preliminary attempts for Neural Machine Translation (NMT), such as concatenating representations of source word and its dependency label together. In this paper, we propose a novel NMT with source dependency representation to improve translation performance of NMT, especially long sentences. Empirical results on NIST Chinese-to-English translation task show that our method achieves 1.6 BLEU improvements on average over a strong NMT system.
Anthology ID:
D17-1304
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2846–2852
Language:
URL:
https://aclanthology.org/D17-1304
DOI:
10.18653/v1/D17-1304
Bibkey:
Cite (ACL):
Kehai Chen, Rui Wang, Masao Utiyama, Lemao Liu, Akihiro Tamura, Eiichiro Sumita, and Tiejun Zhao. 2017. Neural Machine Translation with Source Dependency Representation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2846–2852, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Neural Machine Translation with Source Dependency Representation (Chen et al., EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1304.pdf
Video:
 https://aclanthology.org/D17-1304.mp4