Facebook FAIR's WMT19 News Translation Task Submission

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. read more

PDF Abstract WS 2019 PDF WS 2019 Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Machine Translation WMT2019 English-German Facebook FAIR (ensemble) BLEU score 43.1 # 1
SacreBLEU 42.7 # 2

Methods