Aligning Recommendation and Conversation via Dual Imitation

TL;DR

This paper introduces DICR, a dual imitation framework that explicitly models and aligns user interest shifts in recommendation paths and conversation paths, improving the coherence and accuracy of conversational recommendation systems.

Contribution

The paper proposes a novel dual imitation approach that aligns recommendation and conversation modules via knowledge graph paths, enhancing system performance and explainability.

Findings

DICR outperforms state-of-the-art models in recommendation accuracy.

DICR generates more coherent and explainable responses.

The dual imitation mechanism effectively captures user interest shifts.

Abstract

Human conversations of recommendation naturally involve the shift of interests which can align the recommendation actions and conversation process to make accurate recommendations with rich explanations. However, existing conversational recommendation systems (CRS) ignore the advantage of user interest shift in connecting recommendation and conversation, which leads to an ineffective loose coupling structure of CRS. To address this issue, by modeling the recommendation actions as recommendation paths in a knowledge graph (KG), we propose DICR (Dual Imitation for Conversational Recommendation), which designs a dual imitation to explicitly align the recommendation paths and user interest shift paths in a recommendation module and a conversation module, respectively. By exchanging alignment signals, DICR achieves bidirectional promotion between recommendation and conversation modules and generates high-quality responses with accurate recommendations and coherent explanations. Experiments demonstrate that DICR outperforms the state-of-the-art models on recommendation and conversation performance with automatic, human, and novel explainability metrics.