A Hybrid Approach to Validate Induced Syntactic Relations

Nicolas Béchet 1 Mathieu Roche 2, 1 Jacques Chauché 3, 1
1 TEXTE - Exploration et exploitation de données textuelles
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : We propose in this paper to use NLP approaches to extract and validate induced syntactic relations (Verb-Object). We employ syntactic parser and a semantic proximity measure to extract them. Then, we focus on a Web Validation system, a Semantic-Vector-based approach, and finally we propose approaches to combine both in order to rank induced syntactic relations. The Semantic Vectors approach is a Roget-based method which computes a syntactic relation as a vector. Web Validation uses a search engine to determine the relevance of a syntactic relation. The systems combine Web Validation approach and Semantic Vectors technique. We apply our approaches on corpus of news, using ROC curves to evaluate the results.
Type de document :
Communication dans un congrès
MAW'2009: International Symposium on Mining and Web, in conjunctiion with AINA'09, May 2009, Bradford, United Kingdom. 2009
Liste complète des métadonnées

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00370832
Contributeur : Nicolas Béchet <>
Soumis le : mercredi 25 mars 2009 - 15:12:09
Dernière modification le : jeudi 24 mai 2018 - 15:59:23

Identifiants

  • HAL Id : lirmm-00370832, version 1

Collections

Citation

Nicolas Béchet, Mathieu Roche, Jacques Chauché. A Hybrid Approach to Validate Induced Syntactic Relations. MAW'2009: International Symposium on Mining and Web, in conjunctiion with AINA'09, May 2009, Bradford, United Kingdom. 2009. 〈lirmm-00370832〉

Partager

Métriques

Consultations de la notice

111