@article{2011_Tsimboukakis,
author = "Tsimboukakis, N. and Tambouratzis, George",
abstract = "The main purpose of this paper is the classification of documents in terms of their content. Two systems are presented here that share a two-level architecture that include 1) a word map created via unsupervised learning that functions as a document-representation module and 2) a supervised multilayer-perceptron-based classifier. Two approaches to create word maps are presented and compared; these are based on hidden Markov models (HMMs) and the self-organizing map. A series of experiments is performed on several datasets of text-only documents, which are written in either Greek or in English. A comparison with established methods, such as the support-vector machine (SVM), illustrates the effectiveness of the proposed systems.",
doi = "10.1109/TSMCC.2010.2096416",
journal = "IEEE Transactions on Systems, Man {\&} Cybernetics – Part C",
keywords = "Hidden Markov models; neural-network applications; self-organizing feature maps; text processing",
pages = "in print",
title = "{W}ord map systems for content-based document classification ",
year = "2011",
}