<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1116">
  <Title>Term Aggregation: Mining Synonymous Expressions using Personal Stylistic Variations</Title>
  <Section position="6" start_page="6" end_page="6" type="relat">
    <SectionTitle>
5 Related Work
</SectionTitle>
    <Paragraph position="0"> There have been many approachs to automatic detection of similar words from text. Our method is similar to (Hindle, 1990), (Lin, 1998), and (Gasperin, 2001) in the use of dependency relationships as the word features. Another approach used the words' distribution to cluster the words (Pereira, 1993), and Inoue (Inoue, 1991) also used the word distributional information in the Japanese-English word pairs to resolve the polysemous word problem. null Wu (Wu, 2003) shows one approach to collect synonymous collocation by using translation information. This time we considered only synonymous expression terms, but the phrasal synonymous expression should be the target of aggregation in text analysis.</Paragraph>
    <Paragraph position="1"> Not only synonymous expressions, but abbreviation is one of the most important issues in term aggregation. Youngja (Youngja, 2001) proposed a method for finding abbreviations and their definitions, using the pattern-based rules which were generated automatically and/or manually.</Paragraph>
    <Paragraph position="2"> To re-evaluate the baseline synonym extraction system, we used the authors' writing styles, and there are some researches using this approach. The most famous usage for them is the identification of a unknown author of a certain document (Thisted, 1987).</Paragraph>
  </Section>
class="xml-element"></Paper>