Partner Personas Generation for Dialogue Response Generation
Refereed conference paper presented and published in conference proceedings
CUHK Authors
Other information
AbstractIncorporating 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.
Acceptance Date08/04/2022
All Author(s) ListHongyuan Lu, Wai Lam, Hong Cheng, Helen Meng
Name of ConferenceThe 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Start Date of Conference10/07/2022
End Date of Conference15/07/2022
Place of ConferenceSeattle
Country/Region of ConferenceUnited States of America
Proceedings TitleProceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Year2022
Month7
Day10
PublisherAssociation for Computational Linguistics
Pages5200 - 5212
LanguagesEnglish-United States
KeywordsPartner Personas Generation, Dialogue Response Generation
