Abstract
Traditional machine translation evaluation relies on reference written by humans. While reference-free evaluation gets rid of the constraints of labor-intensive annotations, which can pivot easily to new domains and is more scalable. In this paper, we propose a reference-free evaluation approach that characterizes evaluation as two aspects: (1) fluency: how well the translated text conforms to normal human language usage; (2) faithfulness: how well the translated text reflects the source data. We further split the faithfulness into word-level and sentence-level. Extensive experiments spanning WMT18/19/21 Metrics segment-level daRR and MQM datasets demonstrate that our proposed reference-free approach, ReFreeEval, outperforms SOTA reference-fee metrics like YiSi-2.- Anthology ID:
- 2023.acl-short.55
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 623–636
- Language:
- URL:
- https://aclanthology.org/2023.acl-short.55
- DOI:
- 10.18653/v1/2023.acl-short.55
- Cite (ACL):
- Hanming Wu, Wenjuan Han, Hui Di, Yufeng Chen, and Jinan Xu. 2023. A Holistic Approach to Reference-Free Evaluation of Machine Translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 623–636, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- A Holistic Approach to Reference-Free Evaluation of Machine Translation (Wu et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2023.acl-short.55.pdf