Improving Conversational Recommendation Systems' Quality with Context-Aware Item Meta Information

TL;DR

This paper introduces a new architecture for conversational recommendation systems that leverages item metadata embeddings with pre-trained language models, improving recommendation accuracy and response quality without relying on knowledge graphs.

Contribution

The proposed model simplifies existing approaches by replacing knowledge graph reliance with semantic item metadata embeddings, achieving state-of-the-art results.

Findings

Outperforms previous models on ReDial dataset

Enhances recommendation relevance and response coherence

Reduces engineering effort by avoiding knowledge graph maintenance

Abstract

Conversational recommendation systems (CRS) engage with users by inferring user preferences from dialog history, providing accurate recommendations, and generating appropriate responses. Previous CRSs use knowledge graph (KG) based recommendation modules and integrate KG with language models for response generation. Although KG-based approaches prove effective, two issues remain to be solved. First, KG-based approaches ignore the information in the conversational context but only rely on entity relations and bag of words to recommend items. Second, it requires substantial engineering efforts to maintain KGs that model domain-specific relations, thus leading to less flexibility. In this paper, we propose a simple yet effective architecture comprising a pre-trained language model (PLM) and an item metadata encoder. The encoder learns to map item metadata to embeddings that can reflect the semantic information in the dialog context. The PLM then consumes the semantic-aligned item embeddings together with dialog context to generate high-quality recommendations and responses. Instead of modeling entity relations with KGs, our model reduces engineering complexity by directly converting each item to an embedding. Experimental results on the benchmark dataset ReDial show that our model obtains state-of-the-art results on both recommendation and response generation tasks.