<?xml version="1.0" standalone="yes"?>
<Paper uid="H94-1075">
  <Title>(ALMOST) AUTOMATIC SEMANTIC FEATURE EXTRACTION FROM TECHNICAL TEXT</Title>
  <Section position="8" start_page="381" end_page="381" type="concl">
    <SectionTitle>
6. FINAL COMMENTS
</SectionTitle>
    <Paragraph position="0"> The methodology described in this paper should be useful in acquiring semantic features of a domain with limited human intervention. We also believe that our parsing methodology and the mech~n;Rms for semantic feature acquisition lend themselves very nicely to the development of a simpler and smaller NLP system. This is in contrast to NLP systems that are very large and often use large broad coverage grammars that may take several thousand person-hours to build.</Paragraph>
    <Paragraph position="1"> The simplicity behind starting with phrasal parses and then using these parses to acquire semantic information that leads to better and deeper parses makes our approach s good &amp;quot;poor man's alternative&amp;quot;. The KUDZU system has demonstrated that this simple approach can s/so yield reasonably good results, at least for data or information extraction tasks.</Paragraph>
  </Section>
class="xml-element"></Paper>