Triples-Driven ontology construction with LLMs for Urban Planning compliance
Résumé
Ensuring compliance with urban planning regulations requires both semantic precision and fully interpretable decision processes. In this paper, we present a semi-automated methodology that combines the flexibility of large language models with the rigour of Semantic Web technologies to develop an urban planning ontology from regulatory texts. First, the paper presents a systematic evaluation of eight state-of-the-art large language models on the WebNLG dataset for semantic triple extraction task, using few-shot and chain-ofthought prompting. It then discusses the engineering of a domain-adapted prompt. The resulting triples are partially validated through a two-step procedure that takes into account the topological properties of an underlying graph (corresponding to a raw version of a knowledge graph) and the assessment of Human domain experts.
| Origine | Fichiers éditeurs autorisés sur une archive ouverte |
|---|---|
| Licence |