Facebook FAIR’s WMT19 News Translation Task Submission

Nathan Ng, Kyra Yee, Alexei Baevski, Myle Ott, Michael Auli, Sergey Edunov


Abstract
This paper describes Facebook FAIR’s submission to the WMT19 shared news translation task. We participate in four language directions, English <-> German and English <-> Russian in both directions. Following our submission from last year, our baseline systems are large BPE-based transformer models trained with the FAIRSEQ sequence modeling toolkit. This year we experiment with different bitext data filtering schemes, as well as with adding filtered back-translated data. We also ensemble and fine-tune our models on domain-specific data, then decode using noisy channel model reranking. Our system improves on our previous system’s performance by 4.5 BLEU points and achieves the best case-sensitive BLEU score for the translation direction English→Russian.
Anthology ID:
W19-5333
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:
314–319
Language:
URL:
https://www.aclweb.org/anthology/W19-5333
DOI:
10.18653/v1/W19-5333
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W19-5333.pdf