<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-3020">
  <Title>Graph-based Ranking Algorithms for Sentence Extraction, Applied to Text Summarization</Title>
  <Section position="7" start_page="54" end_page="54" type="relat">
    <SectionTitle>
5 Related Work
</SectionTitle>
    <Paragraph position="0"> Sentence extraction is considered to be an important first step for automatic text summarization. As a consequence, there is a large body of work on algorithms 5Notice that rows two and four in Table 1 are in fact redundant, since the &amp;quot;hub&amp;quot; (&amp;quot;weakness&amp;quot;) variations of the HITS (Positional) algorithms can be derived from their &amp;quot;authority&amp;quot; (&amp;quot;power&amp;quot;) counterparts by reversing the edge orientation in the graphs.</Paragraph>
    <Paragraph position="1"> 6Only seven edges are incident with vertex 15, less than e.g.</Paragraph>
    <Paragraph position="2"> eleven edges incident with vertex 14 - not selected as &amp;quot;important&amp;quot; by TextRank.</Paragraph>
    <Paragraph position="3"> for sentence extraction undertaken as part of the DUC evaluation exercises. Previous approaches include supervised learning (Teufel and Moens, 1997), vectorial similarity computed between an initial abstract and sentences in the given document, or intra-document similarities (Salton et al., 1997). It is also notable the study reported in (Lin and Hovy, 2003b) discussing the usefulness and limitations of automatic sentence extraction for summarization, which emphasizes the need of accurate tools for sentence extraction, as an integral part of automatic summarization systems.</Paragraph>
  </Section>
class="xml-element"></Paper>