BDBComp
Parceria:
SBC
Utilizando Algoritmos de Aprendizado Semi-supervisionados Multi-visao como Rotuladores de Textos

Edson Takashi MatsubaraMaria Carolina MonardGustavo E.A.P.A Batista

The supervised learning approach to learn text classifiers usually requires a large number of labelled training examples. However, labelling is often manually performed, making this process costly and time-consuming. Multiview semi-supervised learning algorithm have the potential of reducing the needof expensive labelled data whenever only a small set of labelled examples is available. In addition, these algorithms require a partitioned description of each example into distinct views. In this work we propose a method where these views can easily be obtained using simple and composed words from text data. Experimental results confirm the suitability of our proposal.

http://www.lbd.dcc.ufmg.br/colecoes/til/2005/0010.pdf

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato: bdbcomp@lbd.dcc.ufmg.br
     Mantida por:
LBD