Abstract
The rapid development of large pretrained language models has revolutionized not only the field of Natural Language Generation (NLG) but also its evaluation. Inspired by the recent work of BARTScore: a metric leveraging the BART language model to evaluate the quality of generated text from various aspects, we introduce DATScore. DATScore uses data augmentation techniques to improve the evaluation of machine translation. Our main finding is that introducing data augmented translations of the source and reference texts is greatly helpful in evaluating the quality of the generated translation. We also propose two novel score averaging and term weighting strategies to improve the original score computing process of BARTScore. Experimental results on WMT show that DATScore correlates better with human meta-evaluations than the other recent state-of-the-art metrics, especially for low-resource languages. Ablation studies demonstrate the value added by our new scoring strategies. Moreover, we report in our extended experiments the performance of DATScore on 3 NLG tasks other than translation.- Anthology ID:
- 2023.findings-eacl.69
- Volume:
- Findings of the Association for Computational Linguistics: EACL 2023
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 942–952
- Language:
- URL:
- https://aclanthology.org/2023.findings-eacl.69
- DOI:
- 10.18653/v1/2023.findings-eacl.69
- Cite (ACL):
- Moussa Kamal Eddine, Guokan Shang, and Michalis Vazirgiannis. 2023. DATScore: Evaluating Translation with Data Augmented Translations. In Findings of the Association for Computational Linguistics: EACL 2023, pages 942–952, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- DATScore: Evaluating Translation with Data Augmented Translations (Kamal Eddine et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-eacl.69.pdf