1170	 Analyzing English Syntax with a Pattern-Learning Parser	 A dependency analysis system based on pattern recognition and learning logic was developed to infer word classes and rules of syntactic combination from experience with text which had been analyzed. The characteristics used to form word classes are the depth in the dependency tree of each word the direction of its governor and the same features for each of its immediate neighbors. Syntactic rules of combination show the relation of a word to its governor in the depth pattern of the sentence. The system was tested on elementary basic English sentences including used earlier by Knowlton in a different learning parser of all sentences. After experience with sentences it was able to generalize with percent accuracy to the next . In accumulative learning trials after the first sentences it averaged a probability of . for accurately parsing each new sentence it encountered. It was concluded that the system is adequate for learning to parse the bulk of basic English but that further development is required before conclusions about its application to ordinary English can be stored. The system is operational and available on the ARPA SDC time-shared computing system.
