Facebook AI’s WAT19 Myanmar-English Translation Task Submission

Peng-Jen Chen, Jiajun Shen, Matthew Le, Vishrav Chaudhary, Ahmed El-Kishky, Guillaume Wenzek, Myle Ott, Marc’Aurelio Ranzato


Abstract
This paper describes Facebook AI’s submission to the WAT 2019 Myanmar-English translation task. Our baseline systems are BPE-based transformer models. We explore methods to leverage monolingual data to improve generalization, including self-training, back-translation and their combination. We further improve results by using noisy channel re-ranking and ensembling. We demonstrate that these techniques can significantly improve not only a system trained with additional monolingual data, but even the baseline system trained exclusively on the provided small parallel dataset. Our system ranks first in both directions according to human evaluation and BLEU, with a gain of over 8 BLEU points above the second best system.
Anthology ID:
D19-5213
Volume:
Proceedings of the 6th Workshop on Asian Translation
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | WAT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
112–122
Language:
URL:
https://aclanthology.org/D19-5213
DOI:
10.18653/v1/D19-5213
Bibkey:
Cite (ACL):
Peng-Jen Chen, Jiajun Shen, Matthew Le, Vishrav Chaudhary, Ahmed El-Kishky, Guillaume Wenzek, Myle Ott, and Marc’Aurelio Ranzato. 2019. Facebook AI’s WAT19 Myanmar-English Translation Task Submission. In Proceedings of the 6th Workshop on Asian Translation, pages 112–122, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Facebook AI’s WAT19 Myanmar-English Translation Task Submission (Chen et al., EMNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-5213.pdf