Transferable Persona-Grounded Dialogues via Grounded Minimal Edits

Chen Henry Wu, Yinhe Zheng, Xiaoxi Mao, Minlie Huang


Abstract
Grounded dialogue models generate responses that are grounded on certain concepts. Limited by the distribution of grounded dialogue data, models trained on such data face the transferability challenges in terms of the data distribution and the type of grounded concepts. To address the challenges, we propose the grounded minimal editing framework, which minimally edits existing responses to be grounded on the given concept. Focusing on personas, we propose Grounded Minimal Editor (GME), which learns to edit by disentangling and recombining persona-related and persona-agnostic parts of the response. To evaluate persona-grounded minimal editing, we present the PersonaMi-nEdit dataset, and experimental results show that GME outperforms competitive baselines by a large margin. To evaluate the transferability, we experiment on the test set of BlendedSkillTalk and show that GME can edit dialogue models’ responses to largely improve their persona consistency while preserving the use of knowledge and empathy.
Anthology ID:
2021.emnlp-main.183
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2368–2382
Language:
URL:
https://aclanthology.org/2021.emnlp-main.183
DOI:
10.18653/v1/2021.emnlp-main.183
Bibkey:
Cite (ACL):
Chen Henry Wu, Yinhe Zheng, Xiaoxi Mao, and Minlie Huang. 2021. Transferable Persona-Grounded Dialogues via Grounded Minimal Edits. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2368–2382, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Transferable Persona-Grounded Dialogues via Grounded Minimal Edits (Wu et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.183.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.183.mp4
Code
 thu-coai/grounded-minimal-edit