PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Utilisation de LSA comme première étape pour la classification des termes d'un corpus spécialisé
Mathieu Roche and Yves Kodratoff
In: MAJECSTIC 2003, 29-31 October 2003, Marseille, France.

Abstract

The term classification for specialized texts is an essential task for various applications (e.g. knowledge extraction in texts, association rules). This paper presents some experimental results to cluster by pairs the terms of a specialized corpus (devoted to "Human Resources"). This clustering is a first crucial step to build a classification of the terms. This paper presents experiments with an automatic method called "Latent Semantic Analysis" (LSA).

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
ID Code:653
Deposited By:Mathieu Roche
Deposited On:29 December 2004