Pruning Terminology Extracted from a Specialized Corpus for CV Ontology Acquisition

Mathieu Roche 1 Yves Kodratoff 2
1 TEXTE - Exploration et exploitation de données textuelles
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : This paper presents an experimental study for extracting a terminology from a corpus made of Curriculum Vitae (CV). This terminology is to be used for ontology acquisition. The choice of the pruning rate of the terminology is crucial relative to the quality of the ontology acquired. In this paper, we investigate this pruning rate by using several evaluation measures (precision, recall, F-measure, and ROC curve).
Type de document :
Communication dans un congrès
Robert Meersman, Zahir Tari, Pilar Herrero et al. OnToContent'06 workshop - On the Move to Meaningful Internet Systems 2006: OTM 2006 Workshops, 2006, Springer-Verlag, pp.1107-1116, 2006, Lecture Notes in Computer Science
Liste complète des métadonnées

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00113165
Contributeur : Mathieu Roche <>
Soumis le : samedi 11 novembre 2006 - 02:16:08
Dernière modification le : jeudi 5 avril 2018 - 12:30:08

Identifiants

  • HAL Id : lirmm-00113165, version 1

Collections

Citation

Mathieu Roche, Yves Kodratoff. Pruning Terminology Extracted from a Specialized Corpus for CV Ontology Acquisition. Robert Meersman, Zahir Tari, Pilar Herrero et al. OnToContent'06 workshop - On the Move to Meaningful Internet Systems 2006: OTM 2006 Workshops, 2006, Springer-Verlag, pp.1107-1116, 2006, Lecture Notes in Computer Science. 〈lirmm-00113165〉

Partager

Métriques

Consultations de la notice

137