NHK’s Lexically-Constrained Neural Machine Translation at WAT 2021

Hideya Mino, Kazutaka Kinugawa, Hitoshi Ito, Isao Goto, Ichiro Yamada, Takenobu Tokunaga


Abstract
This paper describes the system of our team (NHK) for the WAT 2021 Japanese-English restricted machine translation task. In this task, the aim is to improve quality while maintaining consistent terminology for scientific paper translation. This task has a unique feature, where some words in a target sentence are given in addition to a source sentence. In this paper, we use a lexically-constrained neural machine translation (NMT), which concatenates the source sentence and constrained words with a special token to input them into the encoder of NMT. The key to the successful lexically-constrained NMT is the way to extract constraints from a target sentence of training data. We propose two extraction methods: proper-noun constraint and mistranslated-word constraint. These two methods consider the importance of words and fallibility of NMT, respectively. The evaluation results demonstrate the effectiveness of our lexical-constraint method.
Anthology ID:
2021.wat-1.2
Volume:
Proceedings of the 8th Workshop on Asian Translation (WAT2021)
Month:
August
Year:
2021
Address:
Online
Venue:
WAT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
46–52
Language:
URL:
https://aclanthology.org/2021.wat-1.2
DOI:
10.18653/v1/2021.wat-1.2
Bibkey:
Cite (ACL):
Hideya Mino, Kazutaka Kinugawa, Hitoshi Ito, Isao Goto, Ichiro Yamada, and Takenobu Tokunaga. 2021. NHK’s Lexically-Constrained Neural Machine Translation at WAT 2021. In Proceedings of the 8th Workshop on Asian Translation (WAT2021), pages 46–52, Online. Association for Computational Linguistics.
Cite (Informal):
NHK’s Lexically-Constrained Neural Machine Translation at WAT 2021 (Mino et al., WAT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.wat-1.2.pdf