Alleviating the Long-Tail Problem in Conversational Recommender Systems

TL;DR

This paper introduces LOT-CRS, a framework that improves long-tail item recommendations in conversational recommender systems by balancing datasets and employing specialized training tasks.

Contribution

The paper proposes a novel framework with pre-training and fine-tuning strategies to enhance long-tail item recommendation in CRS, addressing dataset imbalance issues.

Findings

Significant improvement in long-tail recommendation performance

Effective dataset balancing enhances diversity in recommendations

Framework is extensible to different CRS datasets

Abstract

Conversational recommender systems (CRS) aim to provide the recommendation service via natural language conversations. To develop an effective CRS, high-quality CRS datasets are very crucial. However, existing CRS datasets suffer from the long-tail issue, \ie a large proportion of items are rarely (or even never) mentioned in the conversations, which are called long-tail items. As a result, the CRSs trained on these datasets tend to recommend frequent items, and the diversity of the recommended items would be largely reduced, making users easier to get bored. To address this issue, this paper presents \textbf{LOT-CRS}, a novel framework that focuses on simulating and utilizing a balanced CRS dataset (\ie covering all the items evenly) for improving \textbf{LO}ng-\textbf{T}ail recommendation performance of CRSs. In our approach, we design two pre-training tasks to enhance the understanding of simulated conversation for long-tail items, and adopt retrieval-augmented fine-tuning with label smoothness strategy to further improve the recommendation of long-tail items. Extensive experiments on two public CRS datasets have demonstrated the effectiveness and extensibility of our approach, especially on long-tail recommendation.