Researchers have developed a reusable framework called Natural Language Knowledge Graph Query (NLKGQ) that enables users to query domain-specific archives using natural language. The system leverages Large Language Models (LLMs) to translate natural language questions into accurate SPARQL queries, which are then executed against a knowledge graph. This framework is designed to be domain-agnostic, with development beginning by capturing domain vocabulary and semantics in a Web Ontology Language (OWL) ontology. The system has demonstrated 100% accuracy in querying neuroimaging research archive metadata, with readable entity names and semantic annotations proving more critical than LLM choice or prompt engineering. AI
IMPACT Enables researchers to access domain-specific data more easily, potentially accelerating scientific discovery.
RANK_REASON Academic paper detailing a new framework for LLM-driven query generation. [lever_c_demoted from research: ic=1 ai=1.0]
- Large Language Models
- Natural Language Knowledge Graph Query
- neuroimaging
- SPARQL
- Web Ontology Language
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
