There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory

TL;DR

This paper enhances knowledge-grounded dialogue systems by incorporating personal memory to improve knowledge selection, leading to more personalized and consistent responses, demonstrated through significant experimental improvements.

Contribution

Introduces a variational approach to model personal memory's influence on knowledge selection in dialogue, addressing personalization gaps in existing methods.

Findings

Outperforms existing methods in automatic evaluation

Achieves higher human evaluation scores

Effectively models personalization in dialogue systems

Abstract

Knowledge-grounded conversation (KGC) shows great potential in building an engaging and knowledgeable chatbot, and knowledge selection is a key ingredient in it. However, previous methods for knowledge selection only concentrate on the relevance between knowledge and dialogue context, ignoring the fact that age, hobby, education and life experience of an interlocutor have a major effect on his or her personal preference over external knowledge. Without taking the personalization issue into account, it is difficult to select the proper knowledge and generate persona-consistent responses. In this work, we introduce personal memory into knowledge selection in KGC to address the personalization issue. We propose a variational method to model the underlying relationship between one's personal memory and his or her selection of knowledge, and devise a learning scheme in which the forward mapping from personal memory to knowledge and its inverse mapping is included in a closed loop so that they could teach each other. Experiment results show that our method outperforms existing KGC methods significantly on both automatic evaluation and human evaluation.