SMT reranked NMT

Terumasa Ehara


Abstract
System architecture, experimental settings and experimental results of the EHR team for the WAT2017 tasks are described. We participate in three tasks: JPCen-ja, JPCzh-ja and JPCko-ja. Although the basic architecture of our system is NMT, reranking technique is conducted using SMT results. One of the major drawback of NMT is under-translation and over-translation. On the other hand, SMT infrequently makes such translations. So, using reranking of n-best NMT outputs by the SMT output, discarding such translations can be expected. We can improve BLEU score from 46.03 to 47.08 by this technique in JPCzh-ja task.
Anthology ID:
W17-5710
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:
119–126
Language:
URL:
https://aclanthology.org/W17-5710
DOI:
Bibkey:
Cite (ACL):
Terumasa Ehara. 2017. SMT reranked NMT. In Proceedings of the 4th Workshop on Asian Translation (WAT2017), pages 119–126, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
SMT reranked NMT (Ehara, WAT 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-5710.pdf