Learning Language Using a Pattern Recognition Approach
William Katke · 1985
A pattern recognition algorithm is described that learns a transition net grammar from positive examples. Two sets of examples-one in English and one in Chinese-are presented. It is hoped that language learning will reduce the knowledge acquisition effort for expert systems and make the natural lan-guage interface to database systems more transportable. The algorithm presented makes a step in that direction by providing a robust parser and reducing special interaction for introduc-tion of new words and terms. We are developing a natural language interface to an expert system for message processing. Both the expert sys-tem and its natural language component take a knowledge-based approach. A learning mechanism has been imple-mented in order to facilitate knowledge acquisition. We believe that learning will extenuate the bottleneck associ-ated with natural language processing. The basic method for acquiring knowledge is through learning by positive example. Up to this point we have successfully developed an algorithm that learns a simple transition net grammar. It also categorizes words by parts of speech. The categories produced are similar to the ones in a standard dictionary. The syntax that is learned rec-ognizes word phrases but makes no attempt to discover dependencies between phrases. This algorithm is a robust parser. It does not need to prompt the user for information about new words such as conjugation rules or part of speech. The fact that the parser can deal with patterns it has never seen before makes it useful in applications that mix languages, such as