Abstract
This paper presents the team TransQuest's participation in Sentence-Level Direct Assessment shared task in WMT 2020. We introduce a simple QE framework based on cross-lingual transformers, and we use it to implement and evaluate two different neural architectures. The proposed methods achieve state-of-the-art results surpassing the results obtained by OpenKiwi, the baseline used in the shared task. We further fine tune the QE framework by performing ensemble and data augmentation. Our approach is the winning solution in all of the language pairs according to the WMT 2020 official results.Citation
Ranasinghe, T., Orasan, C. and Mitkov, R. (2020) TransQuest at WMT2020: Sentence-Level direct assessment. In Proceedings of the Fifth Conference on Machine Translation, pp. 1049–1055, Online. Association for Computational Linguistics..Journal
Fifth Conference on Machine TranslationAdditional Links
https://aclanthology.org/2020.wmt-1.122Type
Conference contributionLanguage
enDescription
© 2020 ACL. 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://aclanthology.org/2020.wmt-1.122ISBN
9781948087810
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by/4.0/