NTT Neural Machine Translation Systems at WAT 2017

Makoto Morishita, Jun Suzuki, Masaaki Nagata


Abstract
In this year, we participated in four translation subtasks at WAT 2017. Our model structure is quite simple but we used it with well-tuned hyper-parameters, leading to a significant improvement compared to the previous state-of-the-art system. We also tried to make use of the unreliable part of the provided parallel corpus by back-translating and making a synthetic corpus. Our submitted system achieved the new state-of-the-art performance in terms of the BLEU score, as well as human evaluation.
Anthology ID:
W17-5706
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:
89–94
Language:
URL:
https://aclanthology.org/W17-5706
DOI:
Bibkey:
Cite (ACL):
Makoto Morishita, Jun Suzuki, and Masaaki Nagata. 2017. NTT Neural Machine Translation Systems at WAT 2017. In Proceedings of the 4th Workshop on Asian Translation (WAT2017), pages 89–94, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
NTT Neural Machine Translation Systems at WAT 2017 (Morishita et al., WAT 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-5706.pdf
Data
ASPEC