| Autor: |
Rei, Ricardo, Guerreiro, Nuno M., Pombal, José, van Stigt, Daan, Treviso, Marcos, Coheur, Luisa, de Souza, José G. C., Martins, André F. T. |
| Rok vydání: |
2023 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
We present the joint contribution of Unbabel and Instituto Superior T\'ecnico 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. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
