Recurrent Neural Network Based Boolean Factor Analysis and its Application to Word Clustering

Abstract

Neural network based algorithm for word clustering as an extension of the neural network based Boolean factor analysis algorithm is introduced. Technique based on a Bayesian procedure has been developed to provide a complete description of factors in terms of component probability and to enhance the accuracy of classification of documents. Method is applied to two types of textual data on Neural Networks in two different languages.

Categories and tags

  • Článek v odborném periodiku