Part of speech tagging with min-max modular neural networks

Part of speech (POS) tagging systems using neural networks have been proposed by Ma et al. (1999). They can tag the untrained data at a practical level of accuracy by training a small Thai corpus with ten thousand order words. The multilayer perceptron type of neural networks used, however, was found to converge slowly and took a very long time to train even the above mentioned small amount of training data. This paper presents an alternative method for solving the POS tagging problems with the min-max modular neural network proposed by Lu and Ito (1997). By using this modular neural network, the part of speech tagging problems can be broken down into a number of independent smaller and simpler sub-problems, and all of the sub-problems can be learned by small network modules in parallel