Large language models as oracles for instantiating ontologies with domain-specific knowledge

arXiv:2404.04108v1 Announce Type: cross
Abstract: Background. Endowing intelligent systems with semantic data commonly requires designing and instantiating ontologies with domain-specific knowledge. Especially in the early phases, those activities are typically performed manually by human experts possibly leveraging on their own experience. The resulting process is therefore time-consuming, error-prone, and often biased by the personal background of the ontology designer. Objective. To mitigate that issue, we propose a novel domain-independent approach to automatically instantiate ontologies with domain-specific knowledge, by leveraging on …

abstract arxiv cs.ai cs.cl cs.ir cs.lg cs.lo data designing domain error experience experts human intelligent intelligent systems knowledge language language models large language large language models ontologies process semantic systems type