Unsupervised Learning of Morphology without Morphemes

The first morphological learner based upon the theory of Whole Word Morphology (Ford et al., 1997) is outlined, and preliminary evaluation results are presented. The program, Whole Word Morphologizer, takes a POS-tagged lexicon as input, induces morphological relationships without attempting to discover or identify morphemes, and is then able to generate new words beyond the learning sample. The accuracy (precision) of the generated new words is as high as 80% using the pure Whole Word theory, and 92% after a post-hoc adjustment is added to the routine. The aim of this project is to develop a computational model employing the theory of whole word morphology (Ford et al., 1997) capable on the one hand of identifying morphological relations within a list of words from any one of a wide variety of languages and, on the other, of putting that knowledge to use in creating previously unseen word forms. A small application called Whole Word Morphologizer which does just this is outlined and ...

• Type: Journal
• Year: 2002
• Where: CORR
• Authors: Sylvain Neuvel, Sean A. Fulop
• Keywords: CORR 2002, Education, Ford Et, Whole Word, Word Morphology