PLATO-KAG: Unsupervised Knowledge-Grounded Conversation via Joint Modeling

Xinxian Huang, Huang He, Siqi Bao, Fan Wang, Hua Wu, Haifeng Wang


Abstract
Large-scale conversation models are turning to leveraging external knowledge to improve the factual accuracy in response generation. Considering the infeasibility to annotate the external knowledge for large-scale dialogue corpora, it is desirable to learn the knowledge selection and response generation in an unsupervised manner. In this paper, we propose PLATO-KAG (Knowledge-Augmented Generation), an unsupervised learning approach for end-to-end knowledge-grounded conversation modeling. For each dialogue context, the top-k relevant knowledge elements are selected and then employed in knowledge-grounded response generation. The two components of knowledge selection and response generation are optimized jointly and effectively under a balanced objective. Experimental results on two publicly available datasets validate the superiority of PLATO-KAG.
Anthology ID:
2021.nlp4convai-1.14
Volume:
Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI
Month:
November
Year:
2021
Address:
Online
Venue:
NLP4ConvAI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
143–154
Language:
URL:
https://aclanthology.org/2021.nlp4convai-1.14
DOI:
10.18653/v1/2021.nlp4convai-1.14
Bibkey:
Cite (ACL):
Xinxian Huang, Huang He, Siqi Bao, Fan Wang, Hua Wu, and Haifeng Wang. 2021. PLATO-KAG: Unsupervised Knowledge-Grounded Conversation via Joint Modeling. In Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI, pages 143–154, Online. Association for Computational Linguistics.
Cite (Informal):
PLATO-KAG: Unsupervised Knowledge-Grounded Conversation via Joint Modeling (Huang et al., NLP4ConvAI 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.nlp4convai-1.14.pdf
Video:
 https://aclanthology.org/2021.nlp4convai-1.14.mp4
Data
Holl-EWizard of Wikipedia