On Mitigating Data Sparsity in Conversational Recommender Systems

2025-07-01

AI Summary

Conversational Recommender Systems (CRS) face dual data sparsity challenges: high lexical diversity in dialogues hinders generalization, while the long-tailed item distribution impedes effective representation learning. To address these issues, we propose DACRS—a novel CRS framework integrating two-stage dialogue augmentation with knowledge graph–guided entity modeling. First, it augments dialogue diversity via semantics-preserving entity replacement. Second, it introduces entity similarity constraints and a dialogue-entity matching attention mechanism to achieve fine-grained preference alignment. Crucially, DACRS requires no additional human annotation, yet significantly enhances user preference modeling under sparse-data conditions. Extensive experiments on two benchmark public datasets demonstrate that DACRS consistently outperforms state-of-the-art methods across all major recommendation metrics, achieving internationally competitive performance.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Preferences
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Conversational recommender systems (CRSs) capture user preference through textual information in dialogues. However, they suffer from data sparsity on two fronts: the dialogue space is vast and linguistically diverse, while the item space exhibits long-tail and sparse distributions. Existing methods struggle with (1) generalizing to varied dialogue expressions due to underutilization of rich textual cues, and (2) learning informative item representations under severe sparsity. To address these problems, we propose a CRS model named DACRS. It consists of three modules, namely Dialogue Augmentation, Knowledge-Guided Entity Modeling, and Dialogue-Entity Matching. In the Dialogue Augmentation module, we apply a two-stage augmentation pipeline to augment the dialogue context to enrich the data and improve generalizability. In the Knowledge-Guided Entity Modeling, we propose a knowledge graph (KG) based entity substitution and an entity similarity constraint to enhance the expressiveness of entity embeddings. In the Dialogue-Entity Matching module, we fuse the dialogue embedding with the mentioned entity embeddings through a dialogue-guided attention aggregation to acquire user embeddings that contain both the explicit and implicit user preferences. Extensive experiments on two public datasets demonstrate the state-of-the-art performance of DACRS.

Problem

• Mitigating data sparsity in conversational recommender systems
• Improving generalization to diverse dialogue expressions
• Enhancing item representations under severe data sparsity

Innovation

• Two-stage augmentation pipeline enriches dialogue context
• Knowledge graph enhances entity embeddings expressiveness
• Dialogue-guided attention aggregates explicit and implicit preferences