Generating and executing complex natural language queries across linked data

Abstract : 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
Type de document :
Communication dans un congrès
International Congress on Medical Informatics, Jan 2015, Sao Paulo, Brazil
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01971222
Contributeur : Limsi Publications <>
Soumis le : dimanche 6 janvier 2019 - 22:28:48
Dernière modification le : mercredi 13 février 2019 - 01:26:35

Identifiants

  • HAL Id : hal-01971222, version 1

Citation

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〉

Partager

Métriques

Consultations de la notice

41