IST-Unbabel Participation in the WMT20 Quality Estimation Shared Task

João Moura, Miguel Vera, Daan van Stigt, Fabio Kepler, André F. T. Martins


Abstract
We present the joint contribution of IST and Unbabel to the WMT 2020 Shared Task on Quality Estimation. Our team participated on all tracks (Direct Assessment, Post-Editing Effort, Document-Level), encompassing a total of 14 submissions. Our submitted systems were developed by extending the OpenKiwi framework to a transformer-based predictor-estimator architecture, and to cope with glass-box, uncertainty-based features coming from neural machine translation systems.
Anthology ID:
2020.wmt-1.119
Volume:
Proceedings of the Fifth Conference on Machine Translation
Month:
November
Year:
2020
Address:
Online
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1029–1036
Language:
URL:
https://aclanthology.org/2020.wmt-1.119
DOI:
Bibkey:
Cite (ACL):
João Moura, Miguel Vera, Daan van Stigt, Fabio Kepler, and André F. T. Martins. 2020. IST-Unbabel Participation in the WMT20 Quality Estimation Shared Task. In Proceedings of the Fifth Conference on Machine Translation, pages 1029–1036, Online. Association for Computational Linguistics.
Cite (Informal):
IST-Unbabel Participation in the WMT20 Quality Estimation Shared Task (Moura et al., WMT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.wmt-1.119.pdf
Video:
 https://slideslive.com/38939643