A Faster Structured-Tag Word-Classification Method

Several methods have been proposed for processing a corpus to induce a tagset for the sublanguage represented by the corpus. This paper examines a structured-tag word classification method introduced by McMahon (1994). Two major variations (non-random initial assignment of words to classes and moving multiple words in parallel) together provide robust non-random results with a speed increase of 200% to 450%, at the cost of slightly lower quality than McMahon’s method’s average quality. Two further variations, retaining information from lessfrequent words and avoiding reclustering closed classes, are proposed for further study.