Naver Labs Europe’s Participation in the Robustness, Chat, and Biomedical Tasks at WMT 2020

Alexandre Berard, Ioan Calapodescu, Vassilina Nikoulina, Jerin Philip


Abstract
This paper describes Naver Labs Europe’s participation in the Robustness, Chat, and Biomedical Translation tasks at WMT 2020. We propose a bidirectional German-English model that is multi-domain, robust to noise, and which can translate entire documents (or bilingual dialogues) at once. We use the same ensemble of such models as our primary submission to all three tasks and achieve competitive results. We also experiment with language model pre-training techniques and evaluate their impact on robustness to noise and out-of-domain translation. For German, Spanish, Italian, and French to English translation in the Biomedical Task, we also submit our recently released multilingual Covid19NMT model.
Anthology ID:
2020.wmt-1.57
Volume:
Proceedings of the Fifth Conference on Machine Translation
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
462–472
Language:
URL:
https://aclanthology.org/2020.wmt-1.57
DOI:
Bibkey:
Cite (ACL):
Alexandre Berard, Ioan Calapodescu, Vassilina Nikoulina, and Jerin Philip. 2020. Naver Labs Europe’s Participation in the Robustness, Chat, and Biomedical Tasks at WMT 2020. In Proceedings of the Fifth Conference on Machine Translation, pages 462–472, Online. Association for Computational Linguistics.
Cite (Informal):
Naver Labs Europe’s Participation in the Robustness, Chat, and Biomedical Tasks at WMT 2020 (Berard et al., WMT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.wmt-1.57.pdf
Video:
 https://slideslive.com/38939577