@inproceedings{ma-etal-2022-self,
title = "{S}el{F}-Eval: Self-supervised Fine-grained Dialogue Evaluation",
author = "Ma, Longxuan and
Zhuang, Ziyu and
Zhang, Weinan and
Li, Mingda and
Liu, Ting",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.coling-1.39/",
pages = "485--495",
abstract = "This paper introduces a novel Self-supervised Fine-grained Dialogue Evaluation framework (SelF-Eval). The core idea is to model the correlation between turn quality and the entire dialogue quality. We first propose a novel automatic data construction method that can automatically assign fine-grained scores for arbitrarily dialogue data. Then we train SelF-Eval with a multi-level contrastive learning schema which helps to distinguish different score levels. Experimental results on multiple benchmarks show that SelF-Eval is highly consistent with human evaluations and better than the state-of-the-art models. We give a detailed analysis of the experiments in this paper. Our code is available on GitHub."
}
Markdown (Informal)
[SelF-Eval: Self-supervised Fine-grained Dialogue Evaluation](https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.coling-1.39/) (Ma et al., COLING 2022)
ACL
- Longxuan Ma, Ziyu Zhuang, Weinan Zhang, Mingda Li, and Ting Liu. 2022. SelF-Eval: Self-supervised Fine-grained Dialogue Evaluation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 485–495, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.