ESTIMATING MEMBERSHIP FUNCTIONS IN A FUZZY NETWORK MODEL FOR PART-OF-SPEECH TAGGING

Part-of-speech (POS) tagging is a process of assigning a POS to each w ord in a sentence. Because many words are often ambiguous in their POS s, POS tagging must be able to select the most proper POS sequence for a given sentence. Recently, probabilistic approaches have shown very promising results to solve such ambiguity problems. Probabilistic appr oaches, however, usually require lots of training data to get reliable probabilities. To alleviate such restriction, we use fuzzy membership functions instead of probability distributions. Such a POS tagging mo del is called a fuzzy network POS tagging model. The membership functi ons are automatically estimated by using probabilities and neural netw orks with a learning algorithm. Experiments show that the performance of the fuzzy network POS tagging model is much better than that of a h idden Markov model under a limited amount of training data. (C) 1996 J ohn Wiley and Sons, Inc.