NICT’s participation to WAT 2019: Multilingualism and Multi-step Fine-Tuning for Low Resource NMT

Raj Dabre, Eiichiro Sumita


Abstract
In this paper we describe our submissions to WAT 2019 for the following tasks: English–Tamil translation and Russian–Japanese translation. Our team,“NICT-5”, focused on multilingual domain adaptation and back-translation for Russian–Japanese translation and on simple fine-tuning for English–Tamil translation . We noted that multi-stage fine tuning is essential in leveraging the power of multilingualism for an extremely low-resource language like Russian–Japanese. Furthermore, we can improve the performance of such a low-resource language pair by exploiting a small but in-domain monolingual corpus via back-translation. We managed to obtain second rank in both tasks for all translation directions.
Anthology ID:
D19-5207
Volume:
Proceedings of the 6th Workshop on Asian Translation
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Toshiaki Nakazawa, Chenchen Ding, Raj Dabre, Anoop Kunchukuttan, Nobushige Doi, Yusuke Oda, Ondřej Bojar, Shantipriya Parida, Isao Goto, Hidaya Mino
Venue:
WAT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
76–80
Language:
URL:
https://aclanthology.org/D19-5207
DOI:
10.18653/v1/D19-5207
Bibkey:
Cite (ACL):
Raj Dabre and Eiichiro Sumita. 2019. NICT’s participation to WAT 2019: Multilingualism and Multi-step Fine-Tuning for Low Resource NMT. In Proceedings of the 6th Workshop on Asian Translation, pages 76–80, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
NICT’s participation to WAT 2019: Multilingualism and Multi-step Fine-Tuning for Low Resource NMT (Dabre & Sumita, WAT 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-5207.pdf