Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation

Haoyu Song, Yan Wang, Wei-Nan Zhang, Xiaojiang Liu, Ting Liu


Abstract
Maintaining a consistent personality in conversations is quite natural for human beings, but is still a non-trivial task for machines. The persona-based dialogue generation task is thus introduced to tackle the personality-inconsistent problem by incorporating explicit persona text into dialogue generation models. Despite the success of existing persona-based models on generating human-like responses, their one-stage decoding framework can hardly avoid the generation of inconsistent persona words. In this work, we introduce a three-stage framework that employs a generate-delete-rewrite mechanism to delete inconsistent words from a generated response prototype and further rewrite it to a personality-consistent one. We carry out evaluations by both human and automatic metrics. Experiments on the Persona-Chat dataset show that our approach achieves good performance.
Anthology ID:
2020.acl-main.516
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5821–5831
Language:
URL:
https://aclanthology.org/2020.acl-main.516
DOI:
10.18653/v1/2020.acl-main.516
Bibkey:
Cite (ACL):
Haoyu Song, Yan Wang, Wei-Nan Zhang, Xiaojiang Liu, and Ting Liu. 2020. Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5821–5831, Online. Association for Computational Linguistics.
Cite (Informal):
Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation (Song et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.516.pdf
Video:
 http://slideslive.com/38928804