<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-0410">
  <Title>Using Summarization for Automatic Briefing Generation</Title>
  <Section position="8" start_page="105" end_page="105" type="relat">
    <SectionTitle>
8 Related Work
</SectionTitle>
    <Paragraph position="0"> There is a fair amount of work on automatic authoring of multimedia presentations, e.g., (Wahlster et al. 93), (Dalai et al. 96), (Mittal et al. 95), (Andre and Rist 97) 5. These efforts differ from ours in two ways: first, unlike us, they are not open-domain; and, second, they don't use summarization components. While such efforts are extremely sophisticated compared to us in multimedia presentation planning and fine-grained coordination and synchronization capabilities, many of the components used in those efforts are clearly applicable to our work. For example, (Andre and Rist 96) include methods for leveraging lifelike characters in this process; these characters can be leveraged in our work as well, to help personify the computer narrator. In addition, our captions, which are very short, rely on canned text based on node labels in the initial script, or based on shallow meta-information generated by the summarization filter (in XML) along with the created media object. (Mittal et al. 95) describe a variety of strategies for generation of longer, more explanatory captions, some of which may be exploited in our work by deepening the level of recta-information, at least for summarization components developed by us.</Paragraph>
    <Paragraph position="1"> In our ability to leverage automatic summarization, our work should be clearly distinguished from work which attempts to format a summary (from an XML representation) into something akin to a Powerpoint briefing, e.g., (Nagao and Hasida 98). Our work, by contrast, is focused on using summarization in generating briefings from an abstract outline.</Paragraph>
  </Section>
class="xml-element"></Paper>