<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1085">
  <Title>Detecting Shifts in News Stories for Paragraph Extraction</Title>
  <Section position="8" start_page="1" end_page="1" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> Thispaperstudiedthe effectiveness ofdetecting sub-ject shifts in paragraph extraction. Future work includes (i) incorporating Named Entity extraction into the method, (ii) applying the method to the TDT2 and TDT3 corpora for quantitative evaluation, and (iii) extending the method to on-line paragraph extraction for real-world applications, which will extract key paragraphs each time the document discusses the target event.</Paragraph>
  </Section>
class="xml-element"></Paper>