<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1079">
  <Title>Generating Overview Summaries of Ongoing Email Thread Discussions</Title>
  <Section position="8" start_page="0" end_page="0" type="concl">
    <SectionTitle>
7 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> The methods described in this paper would form part of a larger email thread summarizer able to identify task boundaries and then initiate the appropriate summarization strategy for that task.</Paragraph>
    <Paragraph position="1"> We have addressed the sub-problem of summarizing the decision-making processes which have been supported by discussions over email.</Paragraph>
    <Paragraph position="2"> Despite the preliminary nature of our investigation, our findings are encouraging and lend support to the view that a combination of simple word vector approaches with singular value decomposition approaches do well at extracting discussion issues.</Paragraph>
    <Paragraph position="3"> Such methods, even with only a simple notion dialogue structure achieve a useful level of recall and precision. We would like to conduct extrinsic experiments to test our assumptions about the usefulness of these summaries. Further investigations will also focus on examine issues of scalability, with regard to group size, and domain independence. We would also like to investigate how issue detection might be integrated with a more complete solution to email thread summarization.</Paragraph>
  </Section>
class="xml-element"></Paper>