<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1019">
  <Title>The Grammatical Function Analysis between Korean Adnoun Clause and Noun Phrase by Using Support Vector Machines</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Many structural ambiguities in Korean sentences are one of the major problems in Korean syntactic analyses. Most of those ambiguities can be classified into either of two categories known as &amp;quot;noun phrase (NP) attachment problem&amp;quot; and &amp;quot;verb phrase (VP) attachment problem&amp;quot;. The NP attachment problem refers to finding the VP which is the head of an NP. On the other hand, the VP attachment problem refers to finding the VP which is the head of a VP.</Paragraph>
    <Paragraph position="1"> In resolving the NP attachment problem, functional morphemes play an important role as they are the crucial elements in characterizing the grammatical function between an NP and its related VP. However, the problem is that there are many NPs that do not have such functional morphemes explicitly attached to each of them.</Paragraph>
    <Paragraph position="2"> This omission makes it difficult to identify the relation between constituents and subsequently to solve the NP attachment problem. Moreover, most Korean sentences are complex sentences, which also makes the problem more complicated.</Paragraph>
    <Paragraph position="3"> In this research, we make an attempt to solve this problem. The focus is on the analysis of the grammatical function between an NP and an embedded adnoun clause with a functional morpheme omitted.</Paragraph>
    <Paragraph position="4"> We adopt Support Vector Machines(SVM) as the device by which a given adnoun clause is analyzed as one of three relative functions (subject, object, or adverbial) or an appositive. Later in this paper (section 3), a brief description of SVM will be given.</Paragraph>
  </Section>
class="xml-element"></Paper>