login
Home / Papers / Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion

Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion

DOI: 10.1145/3394486.3403143Source
295 Citations•2020•
Kun Zhou, Wayne Xin Zhao, Shuqing Bian
journal unavailable

This work incorporates both word-oriented and entity-oriented knowledge graphs~(KG) to enhance the data representations in CRSs, and adopts Mutual Information Maximization to align the word-level andentity-level semantic spaces.

Abstract

Conversational recommender systems (CRS) aim to recommend high-quality items to users through interactive conversations. Although several efforts have been made for CRS, two major issues still remain to be solved. First, the conversation data itself lacks of sufficient contextual information for accurately understanding users' preference. Second, there is a semantic gap between natural language expression and item-level user preference.