eTranslation’s Submissions to the WMT 2019 News Translation Task

Csaba Oravecz, Katina Bontcheva, Adrien Lardilleux, László Tihanyi, Andreas Eisele


Abstract
This paper describes the submissions of the eTranslation team to the WMT 2019 news translation shared task. The systems have been developed with the aim of identifying and following rather than establishing best practices, under the constraints imposed by a low resource training and decoding environment normally used for our production systems. Thus most of the findings and results are transferable to systems used in the eTranslation service. Evaluations suggest that this approach is able to produce decent models with good performance and speed without the overhead of using prohibitively deep and complex architectures.
Anthology ID:
W19-5334
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:
320–326
Language:
URL:
https://aclanthology.org/W19-5334
DOI:
10.18653/v1/W19-5334
Bibkey:
Cite (ACL):
Csaba Oravecz, Katina Bontcheva, Adrien Lardilleux, László Tihanyi, and Andreas Eisele. 2019. eTranslation’s Submissions to the WMT 2019 News Translation Task. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 320–326, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
eTranslation’s Submissions to the WMT 2019 News Translation Task (Oravecz et al., WMT 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/W19-5334.pdf
Poster:
 W19-5334.Poster.pdf