Towards Zero-Shot Persona Dialogue Generation with In-Context Learning

Xinchao Xu, Zeyang Lei, Wenquan Wu, Zheng-Yu Niu, Hua Wu, Haifeng Wang


Abstract
Much work has been done to improve persona consistency by finetuning a pretrained dialogue model on high-quality human-annoated persona datasets. However, these methods still face the challenges of high cost and poor scalability. To this end, we propose a simple-yet-effective approach to significantly improve zero-shot persona consistency via in-context learning. Specifically, we first pre-train a persona-augmented dialogue generation model and then utilize in-context prompting mechanism to realize zero-shot persona customization. Experimental results demonstrate that our method can dramatically improve persona consistency without compromising coherence and informativeness in zero-shot settings.
Anthology ID:
2023.findings-acl.90
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1387–1398
Language:
URL:
https://aclanthology.org/2023.findings-acl.90
DOI:
10.18653/v1/2023.findings-acl.90
Bibkey:
Cite (ACL):
Xinchao Xu, Zeyang Lei, Wenquan Wu, Zheng-Yu Niu, Hua Wu, and Haifeng Wang. 2023. Towards Zero-Shot Persona Dialogue Generation with In-Context Learning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1387–1398, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Towards Zero-Shot Persona Dialogue Generation with In-Context Learning (Xu et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2023.findings-acl.90.pdf