Learning to Improve Persona Consistency in Multi-party Dialogue Generation via Text Knowledge Enhancement

Dongshi Ju, Shi Feng, Pengcheng Lv, Daling Wang, Yifei Zhang


Abstract
In an open-domain dialogue system, the consistent persona is a key factor to generate real and coherent dialogues. Existing methods suffer from the incomprehensive persona tags that have unique and obscure meanings to describe human’s personality. Besides, the addressee information, which is closely related to express personality in multi-party dialogues, has been neglected. In this paper, we construct a multi-party personalized dialogue dataset and propose a graph convolution network model (PersonaTKG) with addressee selecting mechanism that integrates personas, dialogue utterances, and external text knowledge in a unified graph. Extensive experiments have shown that PersonaTKG outperforms the baselines by large margins and effectively improves persona consistency in the generated responses.
Anthology ID:
2022.coling-1.23
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:
298–309
Language:
URL:
https://aclanthology.org/2022.coling-1.23
DOI:
Bibkey:
Cite (ACL):
Dongshi Ju, Shi Feng, Pengcheng Lv, Daling Wang, and Yifei Zhang. 2022. Learning to Improve Persona Consistency in Multi-party Dialogue Generation via Text Knowledge Enhancement. In Proceedings of the 29th International Conference on Computational Linguistics, pages 298–309, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Learning to Improve Persona Consistency in Multi-party Dialogue Generation via Text Knowledge Enhancement (Ju et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.23.pdf
Data
HLA-Chat