KINet: Incorporating Relevant Facts Into Knowledge-Grounded Dialog Generation

Jiaqi Bai, Ze Yang, Jian Yang, Hongcheng Guo, Zhoujun Li

Abstract: Knowledge-grounded conversation has led to great progress in producing informative dialog responses by leveraging external knowledge. This work focuses on two affiliated knowledge grounded conversation tasks: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Knowledge Selection</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Response Generation</i> . Previous work followed the paradigm of selecting the most optimal knowledge piece to guide the conversation towards generating the proper response. However, some knowledge pieces, which are not recognized as optimal, may still benefit response generation. How to effectively leverage these relevant knowledge pieces for response generation still remain a tricky issue. To address this problem, we propose <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><b>KINet</b></small> , a <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">K</b> nowledge <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</b> ncorporation <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Net</b> work, which deals with the problem by boosting both the knowledge selection and the response generation. The proposed model contains a negative enhanced knowledge approximator which improves knowledge selection by enhancing the dense representation of knowledge pieces, and a curriculum knowledge sampler which improves generated responses by incorporating more relevant knowledge pieces in an easy-to-hard manner. We conduct the experiment on two datasets of knowledge-grounded conversations, the results show that the proposed model significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations.