Incorporating Causal Analysis into Diversified and Logical Response Generation

Jiayi Liu, Wei Wei, Zhixuan Chu, Xing Gao, Ji Zhang, Tan Yan, Yulin Kang


Abstract
Although the Conditional Variational Auto-Encoder (CVAE) model can generate more diversified responses than the traditional Seq2Seq model, the responses often have low relevance with the input words or are illogical with the question. A causal analysis is carried out to study the reasons behind, and a methodology of searching for the mediators and mitigating the confounding bias in dialogues is provided. Specifically, we propose to predict the mediators to preserve relevant information and auto-regressively incorporate the mediators into generating process. Besides, a dynamic topic graph guided conditional variational auto-encoder (TGG-CVAE) model is utilized to complement the semantic space and reduce the confounding bias in responses. Extensive experiments demonstrate that the proposed model is able to generate both relevant and informative responses, and outperforms the state-of-the-art in terms of automatic metrics and human evaluations.
Anthology ID:
2022.coling-1.30
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
378–388
Language:
URL:
https://aclanthology.org/2022.coling-1.30
DOI:
Bibkey:
Cite (ACL):
Jiayi Liu, Wei Wei, Zhixuan Chu, Xing Gao, Ji Zhang, Tan Yan, and Yulin Kang. 2022. Incorporating Causal Analysis into Diversified and Logical Response Generation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 378–388, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Incorporating Causal Analysis into Diversified and Logical Response Generation (Liu et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.30.pdf