Learning to Balance the Global Coherence and Informativeness in Knowledge-Grounded Dialogue Generation

Chenxu Niu, Yue Hu, Wei Peng, Yuqiang Xie

Abstract: Recently, knowledge-grounded dialogue has received increasing interest to render the generated responses with more useful and engaging information. However, the knowledge, locally relevant to the user’s utterance, potentially reduces the global coherence of the dialogue. Previous work mainly focuses on retrieving diverse knowledge to assist the response generation whereas resulting in a rough dialogue transition. To alleviate this issue, we propose a History-Adapted Knowledge Copy (HAKC) network to adaptively select context-aware knowledge to ensure the coherence of dialogue. Further, we adopt a contrastive learning framework to enhance the knowledge discrimination ability of HAKC. Experimental results demonstrate the outstanding performance of our model on knowledge selection and response generation tasks as well as the boosted generalization.