Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.01232 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913870335967232 |
|---|---|
| author | Nayyeri, Mojtaba Yogi, Athish A Fathallah, Nadeen Thapa, Ratan Bahadur Tautenhahn, Hans-Michael Schnurpel, Anton Staab, Steffen |
| author_facet | Nayyeri, Mojtaba Yogi, Athish A Fathallah, Nadeen Thapa, Ratan Bahadur Tautenhahn, Hans-Michael Schnurpel, Anton Staab, Steffen |
| contents | Transforming relational databases into knowledge graphs with enriched ontologies enhances semantic interoperability and unlocks advanced graph-based learning and reasoning over data. However, previous approaches either demand significant manual effort to derive an ontology from a database schema or produce only a basic ontology. We present RIGOR, Retrieval-augmented Iterative Generation of RDB Ontologies, an LLM-driven approach that turns relational schemas into rich OWL ontologies with minimal human effort. RIGOR combines three sources via RAG, the database schema and its documentation, a repository of domain ontologies, and a growing core ontology, to prompt a generative LLM for producing successive, provenance-tagged delta ontology fragments. Each fragment is refined by a judge-LLM before being merged into the core ontology, and the process iterates table-by-table following foreign key constraints until coverage is complete. Applied to real-world databases, our approach outputs ontologies that score highly on standard quality dimensions such as accuracy, completeness, conciseness, adaptability, clarity, and consistency, while substantially reducing manual effort. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01232 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Retrieval-Augmented Generation of Ontologies from Relational Databases Nayyeri, Mojtaba Yogi, Athish A Fathallah, Nadeen Thapa, Ratan Bahadur Tautenhahn, Hans-Michael Schnurpel, Anton Staab, Steffen Databases Artificial Intelligence Transforming relational databases into knowledge graphs with enriched ontologies enhances semantic interoperability and unlocks advanced graph-based learning and reasoning over data. However, previous approaches either demand significant manual effort to derive an ontology from a database schema or produce only a basic ontology. We present RIGOR, Retrieval-augmented Iterative Generation of RDB Ontologies, an LLM-driven approach that turns relational schemas into rich OWL ontologies with minimal human effort. RIGOR combines three sources via RAG, the database schema and its documentation, a repository of domain ontologies, and a growing core ontology, to prompt a generative LLM for producing successive, provenance-tagged delta ontology fragments. Each fragment is refined by a judge-LLM before being merged into the core ontology, and the process iterates table-by-table following foreign key constraints until coverage is complete. Applied to real-world databases, our approach outputs ontologies that score highly on standard quality dimensions such as accuracy, completeness, conciseness, adaptability, clarity, and consistency, while substantially reducing manual effort. |
| title | Retrieval-Augmented Generation of Ontologies from Relational Databases |
| topic | Databases Artificial Intelligence |
| url | https://arxiv.org/abs/2506.01232 |