BLASER 2.0: a metric for evaluation and quality estimation of massively multilingual speech and text translation

David Dale, Marta Costa-jussà


Abstract
We present BLASER 2.0, an automatic metric of machine translation quality which supports both speech and text modalities. Compared to its predecessor BLASER (Chen et al., 2023), BLASER 2.0 is based on better underlying text and speech representations that cover 202 text languages and 57 speech ones and extends the training data. BLASER 2.0 comes in two varieties: a reference-based and a reference-free (quality estimation) model. We demonstrate that the reference-free version is applicable not only at the dataset level, for evaluating the overall model performance, but also at the sentence level, for scoring individual translations. In particular, we show its applicability for detecting translation hallucinations and filtering training datasets to obtain more reliable translation models. The BLASER 2.0 models are publicly available at https://github.com/facebookresearch/sonar.
Anthology ID:
2024.findings-emnlp.943
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:
16075–16085
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.943
DOI:
Bibkey:
Cite (ACL):
David Dale and Marta Costa-jussà. 2024. BLASER 2.0: a metric for evaluation and quality estimation of massively multilingual speech and text translation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16075–16085, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
BLASER 2.0: a metric for evaluation and quality estimation of massively multilingual speech and text translation (Dale & Costa-jussà, Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.943.pdf