Unsupervised Learning of Morphology without Morphemes
Computation and Language
2009-09-29 v1 Machine Learning
Abstract
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.
Cite
@article{arxiv.cs/0205072,
title = {Unsupervised Learning of Morphology without Morphemes},
author = {Sylvain Neuvel and Sean A. Fulop},
journal= {arXiv preprint arXiv:cs/0205072},
year = {2009}
}
Comments
10 pages, to appear in Proceedings of the Workshop on Morphological and Phonological Learning 2002, ACL Publications