Keyword identification in Spanish documents using neural networks

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 keywo...

Descripción completa

Detalles Bibliográficos
Autores: Aquino, Germán Osvaldo, Lanzarini, Laura Cristina
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2015
País:Argentina
Institución:Universidad Nacional de La Plata
Repositorio:SEDICI (UNLP)
Idioma:inglés
OAI Identifier:oai:sedici.unlp.edu.ar:10915/50087
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/50087
Access Level:acceso abierto
Palabra clave:Ciencias Informáticas
keyword extraction
autoencoders
Neural nets
Redes Neurales (Computación)
Descripción
Sumario: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.