TREA: Tree-Structure Reasoning Schema for Conversational Recommendation

TL;DR

TREA introduces a tree-structured reasoning schema for conversational recommendation systems, enabling better understanding of complex relationships in dialogues by utilizing hierarchical reasoning with external knowledge.

Contribution

The paper proposes TREA, a novel multi-hierarchical tree reasoning framework that improves causal understanding in conversational recommender systems over existing linear or fixed structures.

Findings

TREA outperforms baseline models on two public datasets.

Hierarchical reasoning improves response relevance and recommendation accuracy.

The approach effectively utilizes external knowledge and historical conversations.

Abstract

Conversational recommender systems (CRS) aim to timely trace the dynamic interests of users through dialogues and generate relevant responses for item recommendations. Recently, various external knowledge bases (especially knowledge graphs) are incorporated into CRS to enhance the understanding of conversation contexts. However, recent reasoning-based models heavily rely on simplified structures such as linear structures or fixed-hierarchical structures for causality reasoning, hence they cannot fully figure out sophisticated relationships among utterances with external knowledge. To address this, we propose a novel Tree structure Reasoning schEmA named TREA. TREA constructs a multi-hierarchical scalable tree as the reasoning structure to clarify the causal relationships between mentioned entities, and fully utilizes historical conversations to generate more reasonable and suitable responses for recommended results. Extensive experiments on two public CRS datasets have demonstrated the effectiveness of our approach.