Concept Indexing for Automated Text Categorization

In this paper we explore the potential of concept indexing with WordNet synsets for Text Categorization, in comparison with the traditional bag of words text representation model. We have performed a series of experiments in which we also test the possibility of using simple yet robust disambiguation methods for concept indexing, and the effectiveness of stoplist-filtering and stemming on the SemCor semantic concordance. Results are not conclusive yet promising.

• Type: Conference
• Year: 2004
• Where: NLDB
• Authors: José María Gómez Hidalgo, José Carlos Cortizo, Enrique Puertas Sanz, Miguel E. Ruiz
• Keywords: Concept Indexing, NLDB 2004, Robust Disambiguation Methods, Words Text Representation