eTranslation’s Submissions to the WMT 2021 News Translation Task

Csaba Oravecz, Katina Bontcheva, David Kolovratník, Bhavani Bhaskar, Michael Jellinghaus, Andreas Eisele


Abstract
The paper describes the 3 NMT models submitted by the eTranslation team to the WMT 2021 news translation shared task. We developed systems in language pairs that are actively used in the European Commission’s eTranslation service. In the WMT news task, recent years have seen a steady increase in the need for computational resources to train deep and complex architectures to produce competitive systems. We took a different approach and explored alternative strategies focusing on data selection and filtering to improve the performance of baseline systems. In the domain constrained task for the French–German language pair our approach resulted in the best system by a significant margin in BLEU. For the other two systems (English–German and English-Czech) we tried to build competitive models using standard best practices.
Anthology ID:
2021.wmt-1.15
Volume:
Proceedings of the Sixth Conference on Machine Translation
Month:
November
Year:
2021
Address:
Online
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
172–179
Language:
URL:
https://aclanthology.org/2021.wmt-1.15
DOI:
Bibkey:
Cite (ACL):
Csaba Oravecz, Katina Bontcheva, David Kolovratník, Bhavani Bhaskar, Michael Jellinghaus, and Andreas Eisele. 2021. eTranslation’s Submissions to the WMT 2021 News Translation Task. In Proceedings of the Sixth Conference on Machine Translation, pages 172–179, Online. Association for Computational Linguistics.
Cite (Informal):
eTranslation’s Submissions to the WMT 2021 News Translation Task (Oravecz et al., WMT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.wmt-1.15.pdf