Towards retrieval-based conversational recommendation

作者：

Highlights：

• We propose a novel approach to retrieval-based conversational recommendation.

• We compare our approach with two neural language generation-based approaches.

• A user study reveals that our system leads to a better quality perception by users.

• Additional analyses shed light on which dialog situations are challenging.

摘要

•We propose a novel approach to retrieval-based conversational recommendation.•We compare our approach with two neural language generation-based approaches.•A user study reveals that our system leads to a better quality perception by users.•Additional analyses shed light on which dialog situations are challenging.

论文关键词：Recommender systems,Conversational recommendation,User study,Information retrieval,End-to-end learning,Dialog systems

论文评审过程：Received 23 November 2021, Revised 8 March 2022, Accepted 10 May 2022, Available online 18 May 2022, Version of Record 24 May 2022.

论文官网地址：https://doi.org/10.1016/j.is.2022.102083