GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems

Lishan Huang, Zheng Ye, Jinghui Qin, Liang Lin, Xiaodan Liang


Abstract
Automatically evaluating dialogue coherence is a challenging but high-demand ability for developing high-quality open-domain dialogue systems. However, current evaluation metrics consider only surface features or utterance-level semantics, without explicitly considering the fine-grained topic transition dynamics of dialogue flows. Here, we first consider that the graph structure constituted with topics in a dialogue can accurately depict the underlying communication logic, which is a more natural way to produce persuasive metrics. Capitalized on the topic-level dialogue graph, we propose a new evaluation metric GRADE, which stands for Graph-enhanced Representations for Automatic Dialogue Evaluation. Specifically, GRADE incorporates both coarse-grained utterance-level contextualized representations and fine-grained topic-level graph representations to evaluate dialogue coherence. The graph representations are obtained by reasoning over topic-level dialogue graphs enhanced with the evidence from a commonsense graph, including k-hop neighboring representations and hop-attention weights. Experimental results show that our GRADE significantly outperforms other state-of-the-art metrics on measuring diverse dialogue models in terms of the Pearson and Spearman correlations with human judgments. Besides, we release a new large-scale human evaluation benchmark to facilitate future research on automatic metrics.
Anthology ID:
2020.emnlp-main.742
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9230–9240
Language:
URL:
https://aclanthology.org/2020.emnlp-main.742
DOI:
10.18653/v1/2020.emnlp-main.742
Bibkey:
Cite (ACL):
Lishan Huang, Zheng Ye, Jinghui Qin, Liang Lin, and Xiaodan Liang. 2020. GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 9230–9240, Online. Association for Computational Linguistics.
Cite (Informal):
GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems (Huang et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/2020.emnlp-main.742.pdf
Video:
 https://slideslive.com/38938945
Code
 li3cmz/GRADE
Data
ConceptNetConvAI2DailyDialog