xTower: A Multilingual LLM for Explaining and Correcting Translation Errors

Marcos Treviso, Nuno Guerreiro, Sweta Agrawal, Ricardo Rei, José Pombal, Tania Vaz, Helena Wu, Beatriz Silva, Daan Stigt, Andre Martins


Abstract
While machine translation (MT) systems are achieving increasingly strong performance on benchmarks, they often produce translations with errors and anomalies. Understanding these errors can potentially help improve the translation quality and user experience. This paper introduces xTower, an open large language model (LLM) built on top of TowerBase designed to provide free-text explanations for translation errors in order to guide the generation of a corrected translation. The quality of the generated explanations by xTower are assessed via both intrinsic and extrinsic evaluation. We ask expert translators to evaluate the quality of the explanations across two dimensions: relatedness towards the error span being explained and helpfulness in error understanding and improving translation quality. Extrinsically, we test xTower across various experimental setups in generating translation corrections, demonstrating significant improvements in translation quality. Our findings highlight xTower’s potential towards not only producing plausible and helpful explanations of automatic translations, but also leveraging them to suggest corrected translations.
Anthology ID:
2024.findings-emnlp.892
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15222–15239
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.892
DOI:
Bibkey:
Cite (ACL):
Marcos Treviso, Nuno Guerreiro, Sweta Agrawal, Ricardo Rei, José Pombal, Tania Vaz, Helena Wu, Beatriz Silva, Daan Stigt, and Andre Martins. 2024. xTower: A Multilingual LLM for Explaining and Correcting Translation Errors. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 15222–15239, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
xTower: A Multilingual LLM for Explaining and Correcting Translation Errors (Treviso et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.892.pdf