BERGAMOT-LATTE submissions for the WMT20 quality estimation shared task
Authors
Fomicheva, MarinaSun, Shuo
Yankovskaya, Lisa
Blain, Frédéric
Chaudhary, Vishrav
Fishel, Mark
Guzmán, Francisco
Specia, Lucia
Issue Date
2020-11-30
Metadata
Show full item recordAbstract
This paper presents our submission to the WMT2020 Shared Task on Quality Estimation (QE). We participate in Task and Task 2 focusing on sentence-level prediction. We explore (a) a black-box approach to QE based on pre-trained representations; and (b) glass-box approaches that leverage various indicators that can be extracted from the neural MT systems. In addition to training a feature-based regression model using glass-box quality indicators, we also test whether they can be used to predict MT quality directly with no supervision. We assess our systems in a multi-lingual setting and show that both types of approaches generalise well across languages. Our black-box QE models tied for the winning submission in four out of seven language pairs inTask 1, thus demonstrating very strong performance. The glass-box approaches also performed competitively, representing a light-weight alternative to the neural-based models.Citation
Fomicheva, M., Sun, S., Yankovskaya, L. et al. (2020) BERGAMOT-LATTE submissions for the WMT20 quality estimation shared task, Proceedings of the Fifth Conference on Machine Translation, November 2020, pp. 1010–1017.Additional Links
https://www.aclweb.org/anthology/2020.wmt-1.116Type
Conference contributionLanguage
enDescription
© 2020 The Authors. Published by Association for Computational Linguistics. This is an open access article available under a Creative Commons licence. The published version can be accessed at the following link on the publisher’s website: https://www.aclweb.org/anthology/2020.wmt-1.116/ISBN
9781948087810
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by/4.0/