Details
| Original language | English |
|---|---|
| Title of host publication | Linking Theory and Practice of Digital Libraries - 29th International Conference on Theory and Practice of Digital Libraries, TPDL 2025, Proceedings |
| Editors | Wolf-Tilo Balke, Koraljka Golub, Yannis Manolopoulos, Kostas Stefanidis, Zheying Zhang |
| Publisher | Springer Science and Business Media Deutschland GmbH |
| Pages | 145-162 |
| Number of pages | 18 |
| ISBN (electronic) | 978-3-032-05409-8 |
| ISBN (print) | 9783032054081 |
| Publication status | Published - 15 Sept 2026 |
| Event | 29th International Conference on Theory and Practice of Digital Libraries, TPDL 2025 - Tampere, Finland Duration: 23 Sept 2025 → 26 Sept 2025 |
Publication series
| Name | Lecture Notes in Computer Science |
|---|---|
| Volume | 16097 LNCS |
| ISSN (Print) | 0302-9743 |
| ISSN (electronic) | 1611-3349 |
Abstract
Scientific research artifacts such as datasets, software or ontologies are essential components of scientific discovery. Yet, the growing volume of such artifacts requires more efficient and relevant search and retrieval systems. We present a neuro-symbolic approach for federated research artifact search, specifically for datasets and software metadata over Resodate and Wikidata. Integrated into the ORKG ASK platform, our system processes user queries through linguistic analysis to extract key terms. These key terms are then used to retrieve and recommend relevant research artifacts from federated sources, ensuring precise and contextually relevant metadata discovery. To further enhance retrieval accuracy, we employ a ranking mechanism that organizes research artifacts based on each user query’s structure and morphological features. We evaluate various key-term extraction methods and ranking approaches, integrating both symbolic and neural techniques. We rigorously evaluate the key-term extraction using Precision, Recall, and F1-score, and assess the re-ranking effectiveness by comparing with human rankings through correlation metrics and LLM-based evaluations. Our experiments show that symbolic methods outperform the neural approach regarding accuracy and response time. As a result, our system offers users more effective and efficient research artifact recommendations.
Keywords
- Federated Search, Key Term Extraction, Neuro-Symbolic Systems
ASJC Scopus subject areas
- Mathematics(all)
- Theoretical Computer Science
- Computer Science(all)
- General Computer Science
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Linking Theory and Practice of Digital Libraries - 29th International Conference on Theory and Practice of Digital Libraries, TPDL 2025, Proceedings. ed. / Wolf-Tilo Balke; Koraljka Golub; Yannis Manolopoulos; Kostas Stefanidis; Zheying Zhang. Springer Science and Business Media Deutschland GmbH, 2026. p. 145-162 (Lecture Notes in Computer Science; Vol. 16097 LNCS).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Neuro-Symbolic Federated Research Artifact Search
AU - Keya, Farhana
AU - Auer, Sören
AU - Jaradeh, Mohamad Yaser
N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026/9/15
Y1 - 2026/9/15
N2 - Scientific research artifacts such as datasets, software or ontologies are essential components of scientific discovery. Yet, the growing volume of such artifacts requires more efficient and relevant search and retrieval systems. We present a neuro-symbolic approach for federated research artifact search, specifically for datasets and software metadata over Resodate and Wikidata. Integrated into the ORKG ASK platform, our system processes user queries through linguistic analysis to extract key terms. These key terms are then used to retrieve and recommend relevant research artifacts from federated sources, ensuring precise and contextually relevant metadata discovery. To further enhance retrieval accuracy, we employ a ranking mechanism that organizes research artifacts based on each user query’s structure and morphological features. We evaluate various key-term extraction methods and ranking approaches, integrating both symbolic and neural techniques. We rigorously evaluate the key-term extraction using Precision, Recall, and F1-score, and assess the re-ranking effectiveness by comparing with human rankings through correlation metrics and LLM-based evaluations. Our experiments show that symbolic methods outperform the neural approach regarding accuracy and response time. As a result, our system offers users more effective and efficient research artifact recommendations.
AB - Scientific research artifacts such as datasets, software or ontologies are essential components of scientific discovery. Yet, the growing volume of such artifacts requires more efficient and relevant search and retrieval systems. We present a neuro-symbolic approach for federated research artifact search, specifically for datasets and software metadata over Resodate and Wikidata. Integrated into the ORKG ASK platform, our system processes user queries through linguistic analysis to extract key terms. These key terms are then used to retrieve and recommend relevant research artifacts from federated sources, ensuring precise and contextually relevant metadata discovery. To further enhance retrieval accuracy, we employ a ranking mechanism that organizes research artifacts based on each user query’s structure and morphological features. We evaluate various key-term extraction methods and ranking approaches, integrating both symbolic and neural techniques. We rigorously evaluate the key-term extraction using Precision, Recall, and F1-score, and assess the re-ranking effectiveness by comparing with human rankings through correlation metrics and LLM-based evaluations. Our experiments show that symbolic methods outperform the neural approach regarding accuracy and response time. As a result, our system offers users more effective and efficient research artifact recommendations.
KW - Federated Search
KW - Key Term Extraction
KW - Neuro-Symbolic Systems
UR - http://www.scopus.com/inward/record.url?scp=105018309166&partnerID=8YFLogxK
U2 - 10.1007/978-3-032-05409-8_10
DO - 10.1007/978-3-032-05409-8_10
M3 - Conference contribution
AN - SCOPUS:105018309166
SN - 9783032054081
T3 - Lecture Notes in Computer Science
SP - 145
EP - 162
BT - Linking Theory and Practice of Digital Libraries - 29th International Conference on Theory and Practice of Digital Libraries, TPDL 2025, Proceedings
A2 - Balke, Wolf-Tilo
A2 - Golub, Koraljka
A2 - Manolopoulos, Yannis
A2 - Stefanidis, Kostas
A2 - Zhang, Zheying
PB - Springer Science and Business Media Deutschland GmbH
T2 - 29th International Conference on Theory and Practice of Digital Libraries, TPDL 2025
Y2 - 23 September 2025 through 26 September 2025
ER -