Alleviating the Long-Tail Problem in Conversational Recommender Systems
This addresses the issue of reduced recommendation diversity for users in conversational recommender systems, though it is incremental as it builds on existing methods to handle data imbalance.
The paper tackles the long-tail problem in conversational recommender systems, where many items are rarely mentioned, by introducing LOT-CRS, a framework that uses simulated balanced datasets and specific training strategies, achieving improved performance on long-tail items as shown in experiments on two public datasets.
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.