Leveraging Historical Interaction Data for Improving Conversational Recommender System

Abstract

Recently, conversational recommender system (CRS) has become an emerging and practical research topic. Most of the existing CRS methods focus on learning effective preference representations for users from conversation data alone. While, we take a new perspective to leverage historical interaction data for improving CRS. For this purpose, we propose a novel pre-training approach to integrating both item-based preference sequence (from historical interaction data) and attribute-based preference sequence (from conversation data) via pre-training methods. We carefully design two pre-training tasks to enhance information fusion between item- and attribute-based preference. To improve the learning performance, we further develop an effective negative sample generator which can produce high-quality negative samples. Experiment results on two real-world datasets have demonstrated the effectiveness of our approach for improving CRS.

arXiv commentAccepted as CIKM short paper

Cited by in corpus (6)

• Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning
• User-Centric Conversational Recommendation with Multi-Aspect User Modeling
• Towards Empathetic Conversational Recommender Systems
• Alleviating the Long-Tail Problem in Conversational Recommender Systems
• Knowledge-Enhanced Conversational Recommendation via Transformer-based Sequential Modelling
• LogicRec: Recommendation with Users' Logical Requirements