Facebook FAIR's WMT19 News Translation Task Submission

Abstract

This paper describes Facebook FAIR's submission to the WMT19 shared news translation task. We participate in two language pairs and four language directions, English German and English Russian. Following our submission from last year, our baseline systems are large BPE-based transformer models trained with the Fairseq sequence modeling toolkit which rely on sampled back-translations. 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 submissions are ranked first in all four directions of the human evaluation campaign. On En->De, our system significantly outperforms other systems as well as human translations. This system improves upon our WMT'18 submission by 4.5 BLEU points.

Full paper on arXiv

Details

arXiv identifier

1907.06616

Published

2019-07-15

Authors

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

Models That Cite This Paper

• Described byblenderbot_small-90M
• Described byblenderbot-3B