NICT’s Supervised Neural Machine Translation Systems for the WMT19 News Translation Task

Raj Dabre, Kehai Chen, Benjamin Marie, Rui Wang, Atsushi Fujita, Masao Utiyama, Eiichiro Sumita


Abstract
In this paper, we describe our supervised neural machine translation (NMT) systems that we developed for the news translation task for Kazakh↔English, Gujarati↔English, Chinese↔English, and English→Finnish translation directions. We focused on leveraging multilingual transfer learning and back-translation for the extremely low-resource language pairs: Kazakh↔English and Gujarati↔English translation. For the Chinese↔English translation, we used the provided parallel data augmented with a large quantity of back-translated monolingual data to train state-of-the-art NMT systems. We then employed techniques that have been proven to be most effective, such as back-translation, fine-tuning, and model ensembling, to generate the primary submissions of Chinese↔English. For English→Finnish, our submission from WMT18 remains a strong baseline despite the increase in parallel corpora for this year’s task.
Anthology ID:
W19-5313
Volume:
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
Month:
August
Year:
2019
Address:
Florence, Italy
Venues:
ACL | WMT | WS
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
168–174
Language:
URL:
https://www.aclweb.org/anthology/W19-5313
DOI:
10.18653/v1/W19-5313
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W19-5313.pdf