Aligning Recommendation and Conversation via Dual Imitation
This work addresses the challenge of ineffective coupling in conversational recommendation systems for users seeking accurate recommendations with coherent explanations, representing an incremental improvement over existing methods.
The paper tackles the problem of aligning recommendation actions with conversation processes in conversational recommendation systems by modeling user interest shifts, proposing DICR which uses dual imitation to align recommendation and conversation paths, resulting in improved performance on recommendation and conversation metrics.
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.