<?xml version="1.0" standalone="yes"?>
<Paper uid="C88-2129">
  <Title>Understanding of Stories for Animation</Title>
  <Section position="5" start_page="623" end_page="624" type="concl">
    <SectionTitle>
6. Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper presents the story understanding mechanism for creating computer animation scenarios. The story understanding mechanism reads a natural language story and creates its scenario for realistic graphic animations. This paper presents three types of hidden actions and relations of actions that must be discovered for realistic animations of stories but which are not explicitly described in the stories, This paper also describes the inference mechanism which recognizes the need for interpolation of these hidden actions and relations. The transition in a story is reflected by chronological sequences of multiple worlds, each of which is monitored by TMS.</Paragraph>
    <Paragraph position="1"> A world holds extracted assertions representing the situation inherent in a sentence. Each world is compared with its neighboring worms, and assertions in the worm are added/deleted/modified in the following three processes: * Causality check among actions.</Paragraph>
    <Paragraph position="2"> * Interpolation of a continuous action beyond a sentence.</Paragraph>
    <Paragraph position="3"> * Interpolation of hidden actions between neighboring sentences.</Paragraph>
    <Paragraph position="4"> The knowledge base is aedon-oriented, hence it is independent of individual stories' domains. Currently, the story understanding mechanism works well for several fables.</Paragraph>
    <Paragraph position="5"> Acknowledgements: The authors would like to express their appreciation for continuous encouragement from Kunihiko Niwa and Takashi Arasekt. This research could not have been started without the encouragement of Kazumoto linuma. Stephen Berkov provided many useful comments.</Paragraph>
  </Section>
class="xml-element"></Paper>