Direct Exploitation of Attention Weights for Translation Quality Estimation

Lisa Yankovskaya, Mark Fishel


Abstract
The paper presents our submission to the WMT2021 Shared Task on Quality Estimation (QE). We participate in sentence-level predictions of human judgments and post-editing effort. We propose a glass-box approach based on attention weights extracted from machine translation systems. In contrast to the previous works, we directly explore attention weight matrices without replacing them with general metrics (like entropy). We show that some of our models can be trained with a small amount of a high-cost labelled data. In the absence of training data our approach still demonstrates a moderate linear correlation, when trained with synthetic data.
Anthology ID:
2021.wmt-1.101
Volume:
Proceedings of the Sixth Conference on Machine Translation
Month:
November
Year:
2021
Address:
Online
Editors:
Loic Barrault, Ondrej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussa, Christian Federmann, Mark Fishel, Alexander Fraser, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Tom Kocmi, Andre Martins, Makoto Morishita, Christof Monz
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
955–960
Language:
URL:
https://aclanthology.org/2021.wmt-1.101
DOI:
Bibkey:
Cite (ACL):
Lisa Yankovskaya and Mark Fishel. 2021. Direct Exploitation of Attention Weights for Translation Quality Estimation. In Proceedings of the Sixth Conference on Machine Translation, pages 955–960, Online. Association for Computational Linguistics.
Cite (Informal):
Direct Exploitation of Attention Weights for Translation Quality Estimation (Yankovskaya & Fishel, WMT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.wmt-1.101.pdf