|Alexandre Berard, Vassilina Nikoulina, Ioan Calapodescu|
|Fifth Conference on Machine Translation (WMT20) at the Conference on Empirical Methods in Natural Language Processing (EMNLP), 19-20 November, 2020|
This paper describes Naver Labs Europe’s participation to 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.