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
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 314–319
- Language:
- URL:
- https://aclanthology.org/W19-5333
- DOI:
- 10.18653/v1/W19-5333
- Cite (ACL):
- Nathan Ng, Kyra Yee, Alexei Baevski, Myle Ott, Michael Auli, and Sergey Edunov. 2019. Facebook FAIR’s WMT19 News Translation Task Submission. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 314–319, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Facebook FAIR’s WMT19 News Translation Task Submission (Ng et al., WMT 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/W19-5333.pdf
- Code
- additional community code