CUNI Systems in WMT21: Revisiting Backtranslation Techniques for English-Czech NMT

Petr Gebauer, Ondřej Bojar, Vojtěch Švandelík, Martin Popel


Abstract
We describe our two NMT systems submitted to the WMT2021 shared task in English-Czech news translation: CUNI-DocTransformer (document-level CUBBITT) and CUNI-Marian-Baselines. We improve the former with a better sentence-segmentation pre-processing and a post-processing for fixing errors in numbers and units. We use the latter for experiments with various backtranslation techniques.
Anthology ID:
2021.wmt-1.7
Volume:
Proceedings of the Sixth Conference on Machine Translation
Month:
November
Year:
2021
Address:
Online
Venues:
EMNLP | WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
123–129
Language:
URL:
https://aclanthology.org/2021.wmt-1.7
DOI:
Bibkey:
Cite (ACL):
Petr Gebauer, Ondřej Bojar, Vojtěch Švandelík, and Martin Popel. 2021. CUNI Systems in WMT21: Revisiting Backtranslation Techniques for English-Czech NMT. In Proceedings of the Sixth Conference on Machine Translation, pages 123–129, Online. Association for Computational Linguistics.
Cite (Informal):
CUNI Systems in WMT21: Revisiting Backtranslation Techniques for English-Czech NMT (Gebauer et al., WMT 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2021.wmt-1.7.pdf