<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2020">
  <Title>Topic-Focused Multi-document Summarization Using an Approximate Oracle Score</Title>
  <Section position="11" start_page="158" end_page="158" type="concl">
    <SectionTitle>
9 Conclusions
</SectionTitle>
    <Paragraph position="0"> We introduced an oracle score based upon the simple model of the probability that a human will choose to include a term in a summary.</Paragraph>
    <Paragraph position="1"> The oracle score demonstrated that for task-based summarization, extract summaries score as well as human-generated abstracts using ROUGE. We  thendemonstratedthatanapproximationoftheoracle score based upon query terms and signature  termsgivesrisetoanautomaticmethodofsummarization, which outperforms the systems entered in DUC05. The approximation also performed verywellinDUC06. Furtherenhancementsbased upon linguistic trimming and redundancy removal via a pivoted QR algorithm give significantly better results.</Paragraph>
  </Section>
class="xml-element"></Paper>