Skip to Main content Skip to Navigation
Conference papers

Etat de l'art : Extraction d'information à partir de thésaurus pour générer une ontologie

Abstract : To participate to the Linked Data for agriculture, we wanted to use AGROVOC that is a multilingual thesaurus maintained by FAO with more than 40,000 terms. We present here a state of the art about techniques to transform a domain ontology from thesaurus. For this we will study ten methodologies along three major axes: the extraction of classes, the extraction of the hierarchy and the relation extraction. We were able to identify some complex aspects from methodologies such as the complexity of disambiguation or validation that led a return to manual techniques.
Keywords : THESAURUS
Document type :
Conference papers
Complete list of metadata

https://hal.inrae.fr/hal-02598575
Contributor : Migration Irstea Publications Connect in order to contact the contributor
Submitted on : Friday, May 15, 2020 - 11:58:44 PM
Last modification on : Monday, June 27, 2022 - 11:33:07 AM

Identifiers

  • HAL Id : hal-02598575, version 1
  • IRSTEA : PUB00038510

Citation

Fabien Amarger, Catherine Roussey, Jean-Pierre Chanet, Ollivier Haemmerlé, Nathalie Jane Hernandez. Etat de l'art : Extraction d'information à partir de thésaurus pour générer une ontologie. 31eme congrés INFormatique des ORganisations et Systèmes d'Information et de Décision (INFORSID), May 2013, Paris, France. pp.16. ⟨hal-02598575⟩

Share

Metrics

Record views

16