On Mitigating Data Sparsity in Conversational Recommender Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913920122355712 |
|---|---|
| author | Zhang, Sixiao Liu, Mingrui Long, Cheng Yuan, Wei Chen, Hongxu Zhao, Xiangyu Yin, Hongzhi |
| author_facet | Zhang, Sixiao Liu, Mingrui Long, Cheng Yuan, Wei Chen, Hongxu Zhao, Xiangyu Yin, Hongzhi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00479 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On Mitigating Data Sparsity in Conversational Recommender Systems Zhang, Sixiao Liu, Mingrui Long, Cheng Yuan, Wei Chen, Hongxu Zhao, Xiangyu Yin, Hongzhi Information Retrieval 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. |
| title | On Mitigating Data Sparsity in Conversational Recommender Systems |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2507.00479 |