MACR: Multi-information Augmented Conversational Recommender

作者：

Highlights：

• Constructing a knowledge graph DBMG with item category information.

• Extracting user preferences for item categories from conversations.

• Fusing category preferences and entity preferences through gating mechanisms.

• Using item introductions to alleviate the lack of information in short dialogues.

摘要

•Constructing a knowledge graph DBMG with item category information.•Extracting user preferences for item categories from conversations.•Fusing category preferences and entity preferences through gating mechanisms.•Using item introductions to alleviate the lack of information in short dialogues.

论文关键词：Conversational recommender system,Knowledge graph,Category information,Item introduction

论文评审过程：Received 7 July 2022, Revised 29 September 2022, Accepted 3 October 2022, Available online 13 October 2022, Version of Record 22 October 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118981