File Information

File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/concl/00/w00-1009_concl.xml

Size: 1,985 bytes

Last Modified: 2025-10-06 13:52:56

<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1009">
  <Title>A Common Theory of Information Fusion from Multiple Text Sources Step One: Cross-Document Structure</Title>
  <Section position="8" start_page="81" end_page="82" type="concl">
    <SectionTitle>
6 Ongoing work and conclusion
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="81" end_page="81" type="sub_section">
      <SectionTitle>
6.1 Ongoing work
</SectionTitle>
      <Paragraph position="0"> We are in the process of performing a user study to collect interagreement data among judges who are asked to label cross-document rhetorical relations.</Paragraph>
      <Paragraph position="1"> We are also currently building a system for automatic identification of relationships in document clusters as well as a library of summarization operators. User preferrenees are used to constrain the summarizers. For example, a user may prefer that in the event of same set of input documents contradiction, both sources of information should be represented in the summary.</Paragraph>
      <Paragraph position="2"> Another user may have preferences for a given source over all others and choose an operator which will only reflect his preferred source. We will facilitate the user's navigation in the space of all possible summarizers. By specifying their preferences, users will build their own summarizers and test them on a collection of documents and then refine them to fit their needs.</Paragraph>
    </Section>
    <Section position="2" start_page="81" end_page="82" type="sub_section">
      <SectionTitle>
6.2 Conclusion
</SectionTitle>
      <Paragraph position="0"> We introduced a theory of cross-document structure based on inter-document relationships such as paraphrase, citation, attribution, modality, and development. We presented a taxonomy of cross-document links. We argued that a CST-based analysis of related documents can facilitate multi-document summarization.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>
Download Original XML