<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1011">
  <Title>Trainable Sentence Planning for Complex Information Presentation in Spoken Dialog Systems</Title>
  <Section position="4" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 SPaRKy Architecture
</SectionTitle>
    <Paragraph position="0"> Information presentation in the MATCH system focuses on user-tailored recommendations and comparisons of restaurants (Walker et al., 2002). Following the bottom-up approach to text-planning described in (Marcu, 1997; Mellish, 1998), each presentation consists of a set of assertions about a set of restaurants and a speci cation of the rhetorical relations that hold between them. Example content plans are shown in Figures 1 and 2. The job of the sentence planner is to choose linguistic resources to realize a content plan and then rank the resulting alternative realizations. Figures 3 and 4 show alternative realizations for the content plans in Figures 1 and 2.</Paragraph>
    <Paragraph position="1"> Alt Realization H SPR</Paragraph>
  </Section>
class="xml-element"></Paper>