Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation

Hanxun Zhong, Zhicheng Dou, Yutao Zhu, Hongjin Qian, Ji-Rong Wen


Abstract
Personalized dialogue systems explore the problem of generating responses that are consistent with the user’s personality, which has raised much attention in recent years. Existing personalized dialogue systems have tried to extract user profiles from dialogue history to guide personalized response generation. Since the dialogue history is usually long and noisy, most existing methods truncate the dialogue history to model the user’s personality. Such methods can generate some personalized responses, but a large part of dialogue history is wasted, leading to sub-optimal performance of personalized response generation. In this work, we propose to refine the user dialogue history on a large scale, based on which we can handle more dialogue history and obtain more abundant and accurate persona information. Specifically, we design an MSP model which consists of three personal information refiners and a personalized response generator. With these multi-level refiners, we can sparsely extract the most valuable information (tokens) from the dialogue history and leverage other similar users’ data to enhance personalization. Experimental results on two real-world datasets demonstrate the superiority of our model in generating more informative and personalized responses.
Anthology ID:
2022.naacl-main.426
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5808–5820
Language:
URL:
https://aclanthology.org/2022.naacl-main.426
DOI:
10.18653/v1/2022.naacl-main.426
Bibkey:
Cite (ACL):
Hanxun Zhong, Zhicheng Dou, Yutao Zhu, Hongjin Qian, and Ji-Rong Wen. 2022. Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5808–5820, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation (Zhong et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.426.pdf