Abstract
We present the contribution of the Unbabel team to the WMT 2020 Shared Task on Metrics. We intend to participate on the segmentlevel, document-level and system-level tracks on all language pairs, as well as the “QE as a Metric” track. Accordingly, we illustrate results of our models in these tracks with reference to test sets from the previous year. Our submissions build upon the recently proposed COMET framework: we train several estimator models to regress on different humangenerated quality scores and a novel ranking model trained on relative ranks obtained from Direct Assessments. We also propose a simple technique for converting segment-level predictions into a document-level score. Overall, our systems achieve strong results for all language pairs on previous test sets and in many cases set a new state-of-the-art.- Anthology ID:
- 2020.wmt-1.101
- 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:
- 911–920
- Language:
- URL:
- https://aclanthology.org/2020.wmt-1.101
- DOI:
- Cite (ACL):
- Ricardo Rei, Craig Stewart, Ana C Farinha, and Alon Lavie. 2020. Unbabel’s Participation in the WMT20 Metrics Shared Task. In Proceedings of the Fifth Conference on Machine Translation, pages 911–920, Online. Association for Computational Linguistics.
- Cite (Informal):
- Unbabel’s Participation in the WMT20 Metrics Shared Task (Rei et al., WMT 2020)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2020.wmt-1.101.pdf