Are References Really Needed? Unbabel-IST 2021 Submission for the Metrics Shared Task

Ricardo Rei, Ana C Farinha, Chrysoula Zerva, Daan van Stigt, Craig Stewart, Pedro Ramos, Taisiya Glushkova, André F. T. Martins, Alon Lavie


Abstract
In this paper, we present the joint contribution of Unbabel and IST to the WMT 2021 Metrics Shared Task. With this year’s focus on Multidimensional Quality Metric (MQM) as the ground-truth human assessment, our aim was to steer COMET towards higher correlations with MQM. We do so by first pre-training on Direct Assessments and then fine-tuning on z-normalized MQM scores. In our experiments we also show that reference-free COMET models are becoming competitive with reference-based models, even outperforming the best COMET model from 2020 on this year’s development data. Additionally, we present COMETinho, a lightweight COMET model that is 19x faster on CPU than the original model, while also achieving state-of-the-art correlations with MQM. Finally, in the “QE as a metric” track, we also participated with a QE model trained using the OpenKiwi framework leveraging MQM scores and word-level annotations.
Anthology ID:
2021.wmt-1.111
Volume:
Proceedings of the Sixth Conference on Machine Translation
Month:
November
Year:
2021
Address:
Online
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1030–1040
Language:
URL:
https://aclanthology.org/2021.wmt-1.111
DOI:
Bibkey:
Cite (ACL):
Ricardo Rei, Ana C Farinha, Chrysoula Zerva, Daan van Stigt, Craig Stewart, Pedro Ramos, Taisiya Glushkova, André F. T. Martins, and Alon Lavie. 2021. Are References Really Needed? Unbabel-IST 2021 Submission for the Metrics Shared Task. In Proceedings of the Sixth Conference on Machine Translation, pages 1030–1040, Online. Association for Computational Linguistics.
Cite (Informal):
Are References Really Needed? Unbabel-IST 2021 Submission for the Metrics Shared Task (Rei et al., WMT 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.wmt-1.111.pdf
Code
 Unbabel/COMET