<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-0907">
  <Title>Story understanding through multi-representation model construction</Title>
  <Section position="5" start_page="2" end_page="2" type="concl">
    <SectionTitle>
5 Conclusions and future work
</SectionTitle>
    <Paragraph position="0"> We have described a model-based multi-representation approach to story understanding that can be used to produce a detailed understanding of a children's story.</Paragraph>
    <Paragraph position="1"> Future work includes the following. First, the program should be parallelized and run on a collection of networked machines so that it can solve much larger problems and solve them quickly to facilitate debugging. Second, the multi-representation axiomatization should be elaborated for a second story, and eventually for the entire early reader corpus. Third, algorithms for minimizing event occurrences in abduction should be added to the program. Fourth, a meta-level reasoning module should be added to formulate event calculus reasoning problems, including setting up the story and segment initial states.</Paragraph>
    <Paragraph position="2"> Fifth, the story understanding system should be hooked up to a semantic parser for input and natural language generator for output. Finally, a natural language question answering module should be added.</Paragraph>
  </Section>
class="xml-element"></Paper>