LLM-guided ontology construction from unstructured texts
A new approach combines compact open-source Large Language Models (LLMs) with ontology learning to extract and structure knowledge from industrial text. This paper evaluates the method on a private French corpus of power-grid incident reports, using LLMs ranging from 7B to 32B parameters. The process extracts entities and relations, generates RDF triples, constructs an OWL ontology, enriches it…
1 source primary source
Key points
- Combines compact LLMs with ontology learning for text processing
- Evaluates approach on French power-grid incident reports corpus
- Improves extraction quality with schema-guided prompting and quantized models
Read the original at arXiv cs.CL · by Abdelhadi Belfadel, Maxence Gagnant, Joseph Kattan, Sana Tmar primary sourceOpen source ↗
Topics · follow one to build your own front page
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- Anthropic's Claude begins 'dreaming' to reorganize memory in tests · 1 src
- John Langford quits Microsoft, declares AI Frontiers over · 1 src
- Anthropic releases study on Claude usage in scientific research · 3 src
- MIT and BASF release CheMeleon for low-data molecular prediction · 2 src
- Anthropic tests Claude agents in EVE Online trading and sabotage detection · 1 src
Comments
via GitHub Discussions