User-Centric Conversational Recommendation with Multi-Aspect User Modeling

TL;DR

This paper introduces a user-centric conversational recommendation model that leverages multi-aspect user preferences from historical sessions and look-alike users, significantly improving recommendation and dialogue quality.

Contribution

The paper proposes a novel UCCR model that systematically models multi-aspect user preferences using historical sessions and look-alike users, enhancing CRS performance.

Findings

Significant improvements in recommendation accuracy.

Enhanced dialogue generation quality.

Effective multi-view user preference modeling.

Abstract

Conversational recommender systems (CRS) aim to provide highquality recommendations in conversations. However, most conventional CRS models mainly focus on the dialogue understanding of the current session, ignoring other rich multi-aspect information of the central subjects (i.e., users) in recommendation. In this work, we highlight that the user's historical dialogue sessions and look-alike users are essential sources of user preferences besides the current dialogue session in CRS. To systematically model the multi-aspect information, we propose a User-Centric Conversational Recommendation (UCCR) model, which returns to the essence of user preference learning in CRS tasks. Specifically, we propose a historical session learner to capture users' multi-view preferences from knowledge, semantic, and consuming views as supplements to the current preference signals. A multi-view preference mapper is conducted to learn the intrinsic correlations among different views in current and historical sessions via self-supervised objectives. We also design a temporal look-alike user selector to understand users via their similar users. The learned multi-aspect multi-view user preferences are then used for the recommendation and dialogue generation. In experiments, we conduct comprehensive evaluations on both Chinese and English CRS datasets. The significant improvements over competitive models in both recommendation and dialogue generation verify the superiority of UCCR.