Year: 2019
Type: conference-paper
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 casesensitive BLEU score for the translation direction English→Russian.
DOI: 10.18653/v1/w19-5333
Authors: Nathan Ng, Kyra Yee, Alexei Baevski, Myle Ott, Michael Auli, Sergey Edunov
Institution: Meta (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2970295111