<?xml version="1.0" standalone="yes"?>
<Paper uid="N04-4005">
  <Title>Enhancing Linguistically Oriented Automatic Keyword Extraction</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> This paper presents experiments on how the performance of automatic keyword extraction can be improved, as measured by keywords previously assigned by professional indexers.</Paragraph>
    <Paragraph position="1"> The keyword extraction algorithm consists of three prediction models that are combined to decide what words or sequences of words in the documents are suitable as keywords. The models, in turn, are built using different definitions of what constitutes a term in a written document.</Paragraph>
  </Section>
class="xml-element"></Paper>