<?xml version="1.0" standalone="yes"?>
<Paper uid="P99-1077">
  <Title>TextTiling VecTile \[ Subjects</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 Related Work
</SectionTitle>
    <Paragraph position="0"> Previous approaches to calculating cohesion differ in the kind of lexical relationship they quantify and in the amount of semantic knowledge they rely on. Topic parsing (Hahn, 1990) utilizes both grammatical cues and semantic inference based on pre-coded domain-specific knowledge More general approaches assess word mmllanty based on thesauri (Morris and Hirst, 1991) or dictionary definitions (Kozima, 1994).</Paragraph>
    <Paragraph position="1"> Methods that solely use observations of patterns in vocabulary use include vocabulary management (Youmans, 1991) and the blocks algorithm im-plemented in the TextTiling system (Hearst, 1997).</Paragraph>
    <Paragraph position="2"> The latter is compared below with the system introduced here.</Paragraph>
    <Paragraph position="3"> A good recent overview of previous approaches can be found in Chapters 4 and 5 of (Reynar, 1998).</Paragraph>
  </Section>
class="xml-element"></Paper>