Neural Machine Translation Using Extracted Context Based on Deep Analysis for the Japanese-English Newswire Task at WAT 2020
Isao Goto, Hideya Mino, Hitoshi Ito, Kazutaka Kinugawa, Ichiro Yamada, Hideki Tanaka
Abstract
This paper describes the system of the NHK-NES team for the WAT 2020 Japanese–English newswire task. There are two main problems in Japanese-English news translation: translation of dropped subjects and compatibility between equivalent translations and English news-style outputs. We address these problems by extracting subjects from the context based on predicate-argument structures and using them as additional inputs, and constructing parallel Japanese-English news sentences equivalently translated from English news sentences. The evaluation results confirm the effectiveness of our context-utilization method.- Anthology ID:
- 2020.wat-1.6
- Volume:
- Proceedings of the 7th Workshop on Asian Translation
- Month:
- December
- Year:
- 2020
- Address:
- Suzhou, China
- Editors:
- Toshiaki Nakazawa, Hideki Nakayama, Chenchen Ding, Raj Dabre, Anoop Kunchukuttan, Win Pa Pa, Ondřej Bojar, Shantipriya Parida, Isao Goto, Hidaya Mino, Hiroshi Manabe, Katsuhito Sudoh, Sadao Kurohashi, Pushpak Bhattacharyya
- Venue:
- WAT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 72–79
- Language:
- URL:
- https://aclanthology.org/2020.wat-1.6
- DOI:
- Cite (ACL):
- Isao Goto, Hideya Mino, Hitoshi Ito, Kazutaka Kinugawa, Ichiro Yamada, and Hideki Tanaka. 2020. Neural Machine Translation Using Extracted Context Based on Deep Analysis for the Japanese-English Newswire Task at WAT 2020. In Proceedings of the 7th Workshop on Asian Translation, pages 72–79, Suzhou, China. Association for Computational Linguistics.
- Cite (Informal):
- Neural Machine Translation Using Extracted Context Based on Deep Analysis for the Japanese-English Newswire Task at WAT 2020 (Goto et al., WAT 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.wat-1.6.pdf