PLATO-KAG: Unsupervised Knowledge-Grounded Conversation via Joint Modeling
Xinxian Huang, He Huang, Siqi Bao, Fan Wang, Hua Ren Wu, Haifeng Wang · 2021
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 knowledgegrounded 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.