<?xml version="1.0" standalone="yes"?>
<Paper uid="W99-0635">
  <Title>Corpus-Based Approach for Nominal Compound Analysis for Korean Based on Linguistic and Statistical Information</Title>
  <Section position="9" start_page="298" end_page="299" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> Many statistical parsers have not taken care of analysis of nominal compounds. Furthermore, many researches which dealt with nominal compound parsing seemed not to have computational approaches tbr linguistic phenomenon in nominal compounds.</Paragraph>
    <Paragraph position="1"> We proposed Korean nominM compound analysis based on linguistic statstical knowledge. Actually, immanent syntactic relations like subject and object as well as structures of nominal compounds arc identified using our nominal compound analyzer and knowledge acquisition method. Syntactic relations identified can be effectively used in semantic interpretation of nominal compound. Moreover, the parser was more accurate by using linguistic knowledge such as structural information and syntactic relation immanent in nouns.</Paragraph>
    <Paragraph position="2"> It is expected that our parsing results including identification of syntactic relations are useful for the application system such as information extraction because many nominal compounds are contained in Korean document bodies and titles, which often represent some events. However, the system still has some difficul- null dependency model (3) results using our algorithm ties, which caused erroneous results. In the future work, we feel it is necessary that lexical I)arameters be transformed into conceptual parameters with large size of semantic knowledge, and filrther studies on linguistic properties of nominals be made.</Paragraph>
  </Section>
class="xml-element"></Paper>