<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2146">
  <Title>Structural disambiguation of morpho-syntactic categorial parsing for Korean *</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Korean is a non-configurational, t)ostpositional, agglutinative language. Postpositions, such as noun-endings, verb-endings, and prefinal verbendings, are morphemes that determine the fnnctional role of NPs (noun phrases) and VPs (verb phrases) in sentences and also transform VPs into NPs or APs (adjective phrases). Since a sequence of prefinal verb-endings, auxiliary verbs and verb-endings can generate hundreds of different usages of the same verb, morpheme-based grammar modeling is considered as a natural consequence for Korean.</Paragraph>
    <Paragraph position="1"> There have been various researches to disambiguate the structural ambiguities in parsing. Lexical and contextual information has been shown to be most crucial for many parsing decisions, such as prepositional-phrase attachment (Hindle and Rooth, 1993). (Charniak, 1995; Collins, 1996) use the lexical intbrmation * This research was partially supported by KOSEF special basic resem'ch 1)rogram (1997.9 ~ 2000.8).</Paragraph>
    <Paragraph position="2"> and (Magerman and Marcus, 1991; Magerman and Weir, 1992) use the contextual information for struct;nral disambiguation. But, there have been few researches that used probability intbrmarion for reducing the spurious ambiguities in choosing the most plausible parse tree of CCG formalism, especially for morpho-syntactic parsing of agglutinative language.</Paragraph>
    <Paragraph position="3"> In this paper, we describe the probabilistic nmthod (e.g., category merge probability, head-head co-occurrence, coverage heuristics) to reduce the spurious atnbiguities and choose the most plausible parse tree for agglutinative languages such as Korean.</Paragraph>
  </Section>
class="xml-element"></Paper>