User Memory Reasoning for Conversational Recommendation

TL;DR

This paper introduces a conversational recommendation model that uses a structured user memory graph to improve interaction naturalness and recommendation accuracy, supported by a new large-scale dataset and a reasoning model.

Contribution

It presents a novel user memory knowledge graph framework and a reasoning model for conversational recommendation, along with a new dataset MGConvRex for training and evaluation.

Findings

The model achieves competitive offline and online results.

The memory graph enables explainable recommendations.

Zero-shot reasoning is effective with the proposed approach.

Abstract

We study a conversational recommendation model which dynamically manages users' past (offline) preferences and current (online) requests through a structured and cumulative user memory knowledge graph, to allow for natural interactions and accurate recommendations. For this study, we create a new Memory Graph (MG) <--> Conversational Recommendation parallel corpus called MGConvRex with 7K+ human-to-human role-playing dialogs, grounded on a large-scale user memory bootstrapped from real-world user scenarios. MGConvRex captures human-level reasoning over user memory and has disjoint training/testing sets of users for zero-shot (cold-start) reasoning for recommendation. We propose a simple yet expandable formulation for constructing and updating the MG, and a reasoning model that predicts optimal dialog policies and recommendation items in unconstrained graph space. The prediction of our proposed model inherits the graph structure, providing a natural way to explain the model's recommendation. Experiments are conducted for both offline metrics and online simulation, showing competitive results.