Abstract
Automatic dialogue response evaluator has been proposed as an alternative to automated metrics and human evaluation. However, existing automatic evaluators achieve only moderate correlation with human judgement and they are not robust. In this work, we propose to build a reference-free evaluator and exploit the power of semi-supervised training and pretrained (masked) language models. Experimental results demonstrate that the proposed evaluator achieves a strong correlation (> 0.6) with human judgement and generalizes robustly to diverse responses and corpora. We open-source the code and data in https://github.com/ZHAOTING/dialog-processing.- Anthology ID:
- 2020.acl-main.4
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 26–33
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.4
- DOI:
- 10.18653/v1/2020.acl-main.4
- Cite (ACL):
- Tianyu Zhao, Divesh Lala, and Tatsuya Kawahara. 2020. Designing Precise and Robust Dialogue Response Evaluators. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 26–33, Online. Association for Computational Linguistics.
- Cite (Informal):
- Designing Precise and Robust Dialogue Response Evaluators (Zhao et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2020.acl-main.4.pdf
- Code
- ZHAOTING/dialog-processing
- Data
- DailyDialog