With an OWL ontology using readable names and annotations, a local Qwen3.6-27B model generates SPARQL for 21 expert questions with 100% accuracy, versus 57% for auto-generated SQL.
Rasheed and Marina Aguado
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Natural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query Generation
With an OWL ontology using readable names and annotations, a local Qwen3.6-27B model generates SPARQL for 21 expert questions with 100% accuracy, versus 57% for auto-generated SQL.