<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-3130">
  <Title>An Abstraction Method Using a Semantic Engine Based on Language Information Structure</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Automatic abstraction, a lnajor natural lauguagc \]n'uecssing application, is difficult to achieve. Luhn\[5\] developed a very simple extraction method that searches for the keywords ill each sentence. This type nf abstraction is easy to accomplish, but its quality is poor. Other abstraction methods\[6, 31 utilize natural language unders~ding (NLU). However NLU is still in the development stage.</Paragraph>
    <Paragraph position="1"> For achieving good practical performance, it is necessary to treat the thformation expressed in a tlocument uniformly so that it can be analyzed with only a small fixed amount of knowledge.</Paragraph>
    <Paragraph position="2"> We propose tile L.IS form which allows inlormatinn about events tO Lvd unilollnly treated, t;urt\[lcl~nore, the semantE engine only uses abstract words, this reduces thc size of the knowledge. So the semuntic engine projects a sentence to a LIS form within a lmdted anloant of knowledge.</Paragraph>
    <Paragraph position="3"> In abstraction, classification is the first step. Classification is performed using unilorln approach, the LIS lkmn. LIS event representation ullow us to select and classify sentences,</Paragraph>
  </Section>
class="xml-element"></Paper>