<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-1411">
  <Title>Acquisition of Lexical Paraphrases from Texts</Title>
  <Section position="3" start_page="2" end_page="2" type="intro">
    <SectionTitle>
3 Approach and Implementation
</SectionTitle>
    <Paragraph position="0"> This section describes our approach to acquiring paraphrase knowledge from a text corpus. We use Perl programming language to implement all of the following processes and experiments.</Paragraph>
    <Section position="1" start_page="2" end_page="2" type="sub_section">
      <SectionTitle>
3.1 Collection of context from corpus
</SectionTitle>
      <Paragraph position="0"> We first define the term context in this paper.</Paragraph>
      <Paragraph position="1"> The context of a certain content word is defined as direct dependency relations between the word and the words that surround it in texts.</Paragraph>
      <Paragraph position="2"> That is, the context of a content word c is, in our sense, defined as the collection of words upon which c directly depends as well as the collection of words that directly depend on c.</Paragraph>
      <Paragraph position="3"> Under this definition, we first collected all of the dependency relations observed in the corpus. Each article is segmented and part-of-speech tagged by the morphological analyzer</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>