<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1132">
  <Title>Learning a Robust Word Sense Disambiguation Model using Hypernyms in Definition Sentences</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Word sense disambiguation (WSD) is the process of selecting the appropriate meaning or sense for a given word in a document. Obviously, WSD is one of the fundamental and important processes needed for many natural language processing (NLP) applications. Over the past decade, many studies have been made on WSD of Japanese. Most current research uses machine learning techniques (Li and Takeuchi, 1997; Murata et al., 2001; Takamura et al., 2001), has achieved good performance. However, as supervised learning methods require word sense-tagged corpora, they often suffer from data sparseness, i.e., words which do not occur frequently in a training corpus can not be disambiguated. Therefore, we cannot use supervised learning algorithms alone in practical NLP applications, especially when it is necessary to disambiguate both high frequency and low frequency words.</Paragraph>
    <Paragraph position="1"> To tackle this problem, this paper proposes a method to combine two WSD classifiers. One is a classifier obtained by supervised learning.</Paragraph>
    <Paragraph position="2"> The learning algorithm used for this classifier is the Support Vector Machine (SVM); this classifier will work well for the disambiguation of high frequency words. The second classifier is the Naive Bayes model, which will work well for the disambiguation of low frequency words.</Paragraph>
    <Paragraph position="3"> In this model, hypernyms extracted from definition sentences in a dictionary are considered in order to overcome data sparseness.</Paragraph>
    <Paragraph position="4"> The details of the SVM classifier are described in Section 2, and the Naive Bayes model in Section 3. The combination of these two classifiers is described in Section 4. The experimental evaluation of the proposed method is reported in Section 5. We mention some related works in Section 6, and conclude the paper in Section 7.</Paragraph>
  </Section>
class="xml-element"></Paper>