RevCore: Review-augmented Conversational Recommendation

TL;DR

RevCore is an innovative conversational recommendation system that integrates reviews to enhance item information and generate more coherent, informative responses, addressing limitations of short dialogue history.

Contribution

This paper introduces RevCore, a novel end-to-end framework that seamlessly incorporates reviews into conversational recommendation, improving both recommendation accuracy and response quality.

Findings

Outperforms baseline models in recommendation accuracy.

Generates more coherent and informative responses.

Effectively utilizes reviews to enrich item information.

Abstract

Existing conversational recommendation (CR) systems usually suffer from insufficient item information when conducted on short dialogue history and unfamiliar items. Incorporating external information (e.g., reviews) is a potential solution to alleviate this problem. Given that reviews often provide a rich and detailed user experience on different interests, they are potential ideal resources for providing high-quality recommendations within an informative conversation. In this paper, we design a novel end-to-end framework, namely, Review-augmented Conversational Recommender (RevCore), where reviews are seamlessly incorporated to enrich item information and assist in generating both coherent and informative responses. In detail, we extract sentiment-consistent reviews, perform review-enriched and entity-based recommendations for item suggestions, as well as use a review-attentive encoder-decoder for response generation. Experimental results demonstrate the superiority of our approach in yielding better performance on both recommendation and conversation responding.