Long Short-Term Planning for Conversational Recommendation Systems

TL;DR

This paper introduces a novel long short-term feedback architecture for conversational recommendation systems, enabling better interaction between recommendation and conversation modules for more natural and effective user engagement.

Contribution

It proposes a new architecture that links long-term recommendation goals with short-term conversational actions, improving the interaction between components.

Findings

Enhanced recommendation accuracy through feedback loop

Improved user engagement with dynamic topic verification

More natural conversational flow in recommendation systems

Abstract

In Conversational Recommendation Systems (CRS), the central question is how the conversational agent can naturally ask for user preferences and provide suitable recommendations. Existing works mainly follow the hierarchical architecture, where a higher policy decides whether to invoke the conversation module (to ask questions) or the recommendation module (to make recommendations). This architecture prevents these two components from fully interacting with each other. In contrast, this paper proposes a novel architecture, the long short-term feedback architecture, to connect these two essential components in CRS. Specifically, the recommendation predicts the long-term recommendation target based on the conversational context and the user history. Driven by the targeted recommendation, the conversational model predicts the next topic or attribute to verify if the user preference matches the target. The balance feedback loop continues until the short-term planner output matches the long-term planner output, that is when the system should make the recommendation.