<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-2012">
  <Title>A Finite-State Model of Georgian Verbal Morphology</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Georgian morphology is largely synthetic, with complex verb forms that can often express the meaning of a whole sentence. Descriptions of Georgian verbal morphology emphasize the large number of inflectional categories; the large number of elements that a verb form can contain; the inter-dependencies in the occurrence of various elements; and the large number of regular, semi-regular, and irregular patterns of formation of verb inflections (cf. Hewitt 1995). All of these factors make computational modeling of Georgian morphology a rather daunting task.</Paragraph>
    <Paragraph position="1"> In this paper, we propose a computational model for parsing and generation of a subset of Georgian verbs that relies on a templatic, word-based analysis of the verbal system rather than assuming compositional rules for combining individual morphemes. We argue that such a model is viable, extensible, and 1This work was in part supported by the Berkeley Language Center. I'd like to thank Lauri Karttunen for introducing me to finite-state morphology and providing an updated version of the software, and Shorena Kurtsikidze and Vakhtang Chikovani for help with the Georgian data. All errors are my own.</Paragraph>
    <Paragraph position="2"> capable of capturing the generalizations inherent in the Georgian verbal system at various levels of regularity. To our knowledge, this is the only computational model of the Georgian verb currently in active development and available to the non-Georgian academic community2.</Paragraph>
  </Section>
class="xml-element"></Paper>