<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-0604">
  <Title>References</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> 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.</Paragraph>
    <Paragraph position="1"> 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 discussed. In particular, this approach is set against the literature on computational morphology as an entirely different way of doing things which has the potential to be generalized to all known varieties of morphology in the world's languages, a feature not shared by previous methods. As it is based on a model of the mental lexicon in which all entries are entire, fully fledged words, this project also serves as an empirical demonstration that a word-based morphological theory that rejects the notion of morpheme as minimal unit of form and meaning (and/or grammatical properties) is viable from the point of view of acquisition as well as generation.</Paragraph>
  </Section>
class="xml-element"></Paper>