<?xml version="1.0" standalone="yes"?>
<Paper uid="A97-1041">
  <Title>Language Generation for Multimedia Healthcare Briefings</Title>
  <Section position="7" start_page="280" end_page="280" type="evalu">
    <SectionTitle>
5 Conclusions and Current
Directions
</SectionTitle>
    <Paragraph position="0"> The context of multimedia briefings for access to healthcare data places new demands on the language generation process. Language generation in MAGIC addresses its user's needs for a brief, yet unambiguous, briefing by coordinating spoken language with the accompanying textual references in the graphical illustration and by combining information into fewer sentences. It also must explicitly represent its decisions as it generates a sentence in order to provide information to the media coordinator for negotiation with graphics.</Paragraph>
    <Paragraph position="1"> Our development of MAGIC is very much an ongoing research project. We are continuing to work on improved coordination of media, use of the syntactic and semantic structure of generated language to improve the quality of the synthesized speech, and analysis of a corpus of radio speech to identify characteristics of formal, spoken language.</Paragraph>
  </Section>
class="xml-element"></Paper>