Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task

30Citations
Citations of this article
12Readers
Mendeley users who have this article in their library.

Abstract

We present the joint contribution of Unbabel and Instituto Superior Técnico to the WMT 2023 Shared Task on Quality Estimation (QE). Our team participated on all tasks: sentence- and word-level quality prediction (task 1) and fine-grained error span detection (task 2). For all tasks, we build on the COMETKIWI-22 model (Rei et al., 2022b). Our multilingual approaches are ranked first for all tasks, reaching state-of-the-art performance for quality estimation at word-, span- and sentence-level granularity. Compared to the previous state-of-the-art, COMETKIWI-22, we show large improvements in correlation with human judgements (up to 10 Spearman points). Moreover, we surpass the second-best multilingual submission to the shared-task with up to 3.8 absolute points.

Cite

CITATION STYLE

APA

Rei, R., Guerreiro, N. M., Pombal, J., van Stigt, D., Treviso, M., Coheur, L., … Martins, A. F. T. (2023). Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task. In Conference on Machine Translation - Proceedings (pp. 839–846). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.wmt-1.73

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free