<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-1005">
  <Title>Vocabulary Usage in Newswire Summaries</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> Analysis of 9000 manually written summaries of newswire stories used in four Document Understanding Conferences indicates that approximately 40% of their lexical items do not occur in the source document. A further comparison of different summaries of the same document shows agreement on 28% of their vocabulary. It can be argued that these relationships establish a performance ceiling for automated summarization systems which do not perform syntactic and semantic analysis on the source document.</Paragraph>
  </Section>
class="xml-element"></Paper>