- Published
- 19 November 2020
- Conference item
Naver Labs Europe's Participation in the Robustness, Chat, and Biomedical Tasks at WMT 2020
- Authors
- Source
- Proceedings of the Fifth Conference on Machine Translation
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.
Rights
ACL materials are Copyright © 1963–2021 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License. https://creativecommons.org/licenses/by/4.0/
Cite as
Berard, A., Calapodescu, I., Nikoulina, V. & Philip, J. 2020, 'Naver Labs Europe's Participation in the Robustness, Chat, and Biomedical Tasks at WMT 2020', Proceedings of the Fifth Conference on Machine Translation, pp. 462-472. https://www.research.ed.ac.uk/portal/en/publications/naver-labs-europes-participation-in-the-robustness-chat-and-biomedical-tasks-at-wmt-2020(560eed06-86e7-4b8a-82f5-b9cae2486ddb).html