<?xml version="1.0" standalone="yes"?>
<Paper uid="A88-1018">
  <Title>INTEGRATING TOP-DOWN AND BOTTOM-UP STRATEGIES IN A TEXT PROCESSING SYSTEM</Title>
  <Section position="14" start_page="134" end_page="134" type="concl">
    <SectionTitle>
CONCLUSION
</SectionTitle>
    <Paragraph position="0"> The analysis of extended texts presents an extremely difficult problem for artificial intelligence systems. Bottom-up processing, or linguistic analysis, is necessary to avoid missing information that may be explicitly, although subtly, conveyed by the text. Top-down, or expectation-driven processing, is essential for the understanding of language in context. Most text analysis systems have relied too heavily on one strategy.</Paragraph>
    <Paragraph position="1"> SCISOR represents a unique integration of knowledge sources to achieve robust and reliable extraction of information from naturally occurring texts in constrained domains. Its ability to use lexical and syntactic knowledge when available separates it from purely expectation-driven semantic analyzers. At the same time, its lack of reliance on any single source of information and multiple &amp;quot;fall-back&amp;quot; heuristics give the system the ability to focus attention and processing on those items of particular interest to be extracted.</Paragraph>
  </Section>
class="xml-element"></Paper>