Improving Japanese-to-English Neural Machine Translation by Paraphrasing the Target Language

Yuuki Sekizawa, Tomoyuki Kajiwara, Mamoru Komachi

[How to correct problems with metadata yourself]

Abstract
Neural machine translation (NMT) produces sentences that are more fluent than those produced by statistical machine translation (SMT). However, NMT has a very high computational cost because of the high dimensionality of the output layer. Generally, NMT restricts the size of vocabulary, which results in infrequent words being treated as out-of-vocabulary (OOV) and degrades the performance of the translation. In evaluation, we achieved a statistically significant BLEU score improvement of 0.55-0.77 over the baselines including the state-of-the-art method.
Anthology ID:
W17-5703
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:
64–69
Language:
URL:
https://aclanthology.org/W17-5703
DOI:
Bibkey:
Cite (ACL):
Yuuki Sekizawa, Tomoyuki Kajiwara, and Mamoru Komachi. 2017. Improving Japanese-to-English Neural Machine Translation by Paraphrasing the Target Language. In Proceedings of the 4th Workshop on Asian Translation (WAT2017), pages 64–69, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Improving Japanese-to-English Neural Machine Translation by Paraphrasing the Target Language (Sekizawa et al., WAT 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/W17-5703.pdf
Data
ASPEC
PDF Search