Generating and executing complex natural language queries across linked data

Thierry Hamon (1, 2) , Fleur Mougin (3) , Natalia Grabar (4)

1 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
2 UP13 - Université Paris 13
3 Epidémiologie et Biostatistique [Bordeaux]
4 STL - Savoirs, Textes, Langage (STL) - UMR 8163

With the recent and intensive research in the biomedical area, the knowledge accumulated is disseminated through various knowledge bases. The combined exploitation of this knowledge is important, which requires to create links be- tween these bases and 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 http://search.cpan.org/~thhamon/RDF-NLP-SPARQLQuery

Mots clés: Natural Language Processing; SPARQL; Linked Data; biomedical domain; semantic resources; frames; Knowledge Databases

Domaines: Informatique [cs]; Informatique et langage [cs.CL]

Thierry Hamon, Fleur Mougin, Natalia Grabar. Generating and executing complex natural language queries across linked data. International Congress on Medical Informatics, Jan 2015, Sao Paulo, Brazil. ⟨hal-01971222⟩