<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2146">
  <Title>Structural disambiguation of morpho-syntactic categorial parsing for Korean *</Title>
  <Section position="6" start_page="1005" end_page="1005" type="concl">
    <SectionTitle>
5 Summary
</SectionTitle>
    <Paragraph position="0"> We developed a morpho-syntactic categorial parser of Korean and devised a morpheme-based statistical structural disambiguation s(;henles.</Paragraph>
    <Paragraph position="1"> Through the KCCG model, we successthlly handled difficult Korean modeling problems, inchtding relative free-word ordering, coordination, and case-marking, during the parsing. To extract the most plausible parse trees ti'om the parse forest, we have presented basic statistical techniques using the lexical and contextual information such as morpheme-category probability and category merge probability.</Paragraph>
    <Paragraph position="2"> Two different nature of heuristics, head-head co-occurrence and coverage scores, are also developed and tested to augment the basic statistical model. Each of them demonstrates reasonable t)ertbrmance increase.</Paragraph>
    <Paragraph position="3"> The next step will be to devise more heuristics and good combination strategies tbr the different nature of heuristics.</Paragraph>
  </Section>
class="xml-element"></Paper>