Send to

Choose Destination

Generating and Executing Complex Natural Language Queries across Linked Data.

Author information

LIMSI-CNRS, Orsay, France; Université Paris 13, Sorbonne Paris Cité, France.
Université Bordeaux, ISPED, Centre INSERM U897, ERIAS, France.
STL UMR8163 CNRS, Université Lille 3, France.


With the recent and intensive research in the biomedical area, the knowledge accumulated is disseminated through various knowledge bases. Links between these knowledge bases are needed in order to use them jointly. Linked Data, SPARQL language, and interfaces in Natural Language question-answering provide interesting solutions for querying such knowledge bases. We propose a method for translating natural language questions in SPARQL queries. We use Natural Language Processing tools, semantic resources, and the RDF triples description. The method is designed on 50 questions over 3 biomedical knowledge bases, and evaluated on 27 questions. It achieves 0.78 F-measure on the test set. The method for translating natural language questions into SPARQL queries is implemented as Perl module available at thhamon/RDF-NLP-SPARQLQuery.

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for IOS Press
Loading ...
Support Center