Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2508.13394 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912824348901376 |
|---|---|
| author | Do, Lam Thanh Van Nguyen, Linh Li, Jiayu Fu, David Chang, Kevin Chen-Chuan |
| author_facet | Do, Lam Thanh Van Nguyen, Linh Li, Jiayu Fu, David Chang, Kevin Chen-Chuan |
| contents | Identifying relevant research concepts is crucial for effective scientific search. However, primary sparse retrieval methods often lack concept-aware representations. To address this, we propose CASPER, a sparse retrieval model for scientific search that utilizes both tokens and keyphrases as representation units (i.e., dimensions in the sparse embedding space). This enables CASPER to represent queries and documents via research concepts and match them at both granular and conceptual levels. Furthermore, we construct training data by leveraging abundant scholarly references (including titles, citation contexts, author-assigned keyphrases, and co-citations), which capture how research concepts are expressed in diverse settings. Empirically, CASPER outperforms strong dense and sparse retrieval baselines across eight scientific retrieval benchmarks. We also explore the effectiveness-efficiency trade-off via representation pruning and demonstrate CASPER's interpretability by showing that it can serve as an effective and efficient keyphrase generation model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_13394 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CASPER: Concept-integrated Sparse Representation for Scientific Retrieval Do, Lam Thanh Van Nguyen, Linh Li, Jiayu Fu, David Chang, Kevin Chen-Chuan Information Retrieval Identifying relevant research concepts is crucial for effective scientific search. However, primary sparse retrieval methods often lack concept-aware representations. To address this, we propose CASPER, a sparse retrieval model for scientific search that utilizes both tokens and keyphrases as representation units (i.e., dimensions in the sparse embedding space). This enables CASPER to represent queries and documents via research concepts and match them at both granular and conceptual levels. Furthermore, we construct training data by leveraging abundant scholarly references (including titles, citation contexts, author-assigned keyphrases, and co-citations), which capture how research concepts are expressed in diverse settings. Empirically, CASPER outperforms strong dense and sparse retrieval baselines across eight scientific retrieval benchmarks. We also explore the effectiveness-efficiency trade-off via representation pruning and demonstrate CASPER's interpretability by showing that it can serve as an effective and efficient keyphrase generation model. |
| title | CASPER: Concept-integrated Sparse Representation for Scientific Retrieval |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2508.13394 |