Partner Personas Generation for Dialogue Response Generation

Hongyuan Lu, Wai Lam, Hong Cheng, Helen Meng


Abstract
Incorporating personas information allows diverse and engaging responses in dialogue response generation. Unfortunately, prior works have primarily focused on self personas and have overlooked the value of partner personas. Moreover, in practical applications, the availability of the gold partner personas is often not the case. This paper attempts to tackle these issues by offering a novel framework that leverages automatic partner personas generation to enhance the succeeding dialogue response generation. Our framework employs reinforcement learning with a dedicatedly designed critic network for reward judgement. Experimental results from automatic and human evaluations indicate that our framework is capable of generating relevant, interesting, coherent and informative partner personas, even compared to the ground truth partner personas. This enhances the succeeding dialogue response generation, which surpasses our competitive baselines that condition on the ground truth partner personas.
Anthology ID:
2022.naacl-main.382
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:
5200–5212
Language:
URL:
https://aclanthology.org/2022.naacl-main.382
DOI:
10.18653/v1/2022.naacl-main.382
Bibkey:
Cite (ACL):
Hongyuan Lu, Wai Lam, Hong Cheng, and Helen Meng. 2022. Partner Personas Generation for Dialogue Response Generation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5200–5212, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Partner Personas Generation for Dialogue Response Generation (Lu et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.382.pdf
Software:
 2022.naacl-main.382.software.zip