TransQuest at WMT2020: Sentence-Level Direct Assessment

Tharindu Ranasinghe, Constantin Orasan, Ruslan Mitkov


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.
Anthology ID:
2020.wmt-1.122
Volume:
Proceedings of the Fifth Conference on Machine Translation
Month:
November
Year:
2020
Address:
Online
Editors:
Loïc Barrault, Ondřej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussà, Christian Federmann, Mark Fishel, Alexander Fraser, Yvette Graham, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, André Martins, Makoto Morishita, Christof Monz, Masaaki Nagata, Toshiaki Nakazawa, Matteo Negri
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1049–1055
Language:
URL:
https://aclanthology.org/2020.wmt-1.122
DOI:
Bibkey:
Cite (ACL):
Tharindu Ranasinghe, Constantin Orasan, and Ruslan Mitkov. 2020. TransQuest at WMT2020: Sentence-Level Direct Assessment. In Proceedings of the Fifth Conference on Machine Translation, pages 1049–1055, Online. Association for Computational Linguistics.
Cite (Informal):
TransQuest at WMT2020: Sentence-Level Direct Assessment (Ranasinghe et al., WMT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.wmt-1.122.pdf
Video:
 https://slideslive.com/38939607
Code
 tharindudr/transQuest