Regressive Ensemble for Machine Translation Quality Evaluation

Varování

Publikace nespadá pod Filozofickou fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.

Autoři

ŠTEFÁNIK Michal NOVOTNÝ Vít SOJKA Petr

Rok publikování 2021
Druh Článek ve sborníku
Konference Proceedings of EMNLP 2021 Sixth Conference on Machine Translation (WMT 21)
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www preprint
Klíčová slova machine translation; translation quality metrics; regressive ensemble for machine translation quality evaluation
Popis This work introduces a simple regressive ensemble for evaluating machine translation quality based on a set of novel and established metrics. We evaluate the ensemble using a correlation to expert-based MQM scores of the WMT 2021 Metrics workshop. In both monolingual and zero-shot cross-lingual settings, we show a significant performance improvements over single systems. In the cross-lingual settings, we also demonstrate that an ensemble approach is well-applicable to unseen languages. Furthermore, we identify a strong reference-free baseline that consistently outperforms the commonly-used BLEU and METEOR measures and significantly improves our ensemble's performance.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.