Rethinking and Refining the Distinct Metric
Siyang Liu, Sahand Sabour, Yinhe Zheng, Pei Ke, Xiaoyan Zhu, Minlie Huang
Abstract
Distinct is a widely used automatic metric for evaluating diversity in language generation tasks. However, we observed that the original approach to calculating distinct scores has evident biases that tend to assign higher penalties to longer sequences. We refine the calculation of distinct scores by scaling the number of distinct tokens based on their expectations. We provide both empirical and theoretical evidence to show that our method effectively removes the biases existing in the original distinct score. Our experiments show that our proposed metric, Expectation-Adjusted Distinct (EAD), correlates better with human judgment in evaluating response diversity.To assist future research, we provide an example implementation at https://github.com/lsy641/Expectation-Adjusted-Distinct.- Anthology ID:
- 2022.acl-short.86
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 762–770
- Language:
- URL:
- https://aclanthology.org/2022.acl-short.86
- DOI:
- 10.18653/v1/2022.acl-short.86
- Cite (ACL):
- Siyang Liu, Sahand Sabour, Yinhe Zheng, Pei Ke, Xiaoyan Zhu, and Minlie Huang. 2022. Rethinking and Refining the Distinct Metric. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 762–770, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Rethinking and Refining the Distinct Metric (Liu et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2022.acl-short.86.pdf
- Code
- lsy641/expectation-adjusted-distinct
- Data
- DailyDialog