Keyword Identification in Spanish Documents using Neural Networks

Abstract

The large amount of textual information digitally available today gives rise to the need for effective means of indexing, searching and retrieving this information. Keywords are used to describe briefly and precisely the contents of a textual document. In this paper we present an algorithm for keyword extraction from documents written in Spanish.This algorithm combines autoencoders, which are adequate for highly unbalanced classification problems, with the discriminative power of conventional binary classifiers. In order to improve its performance on larger and more diverse datasets, our algorithm trains several models of each kind through bagging.