<?xml version="1.0" standalone="yes"?>
<Paper uid="P95-1043">
  <Title>From route descriptions to sketches: a model for a text-to-image translator</Title>
  <Section position="6" start_page="300" end_page="300" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> Computer translation of route descriptions into sketches raises some interesting issues. Firstly, one has to investigate the relationships between the linguistic and the graphic modes, the constraints and possibilities which appear while generating images from linguistic descriptions.</Paragraph>
    <Paragraph position="1"> Secondly, a thorough linguistic analysis of route descriptions is necessary. We have used a discourse based approach and analyze &amp;quot;local&amp;quot; linguistic elements by filtering them through the discourse structure, described at the &amp;quot;global&amp;quot; level. Our goal is to build a linguistic model for the text type &amp;quot;route description&amp;quot;.</Paragraph>
    <Paragraph position="2"> Another interesting problem is the form and the derivation of the conceptual representation of the described route. We believe that it cannot be directly obtained from the linguistic material itself. During the understanding process, the linguistic meaning has to be represented before the conceptual representation can be created. That is why we need a two-stage internal representation, based on specific linguistic and conceptual models.</Paragraph>
  </Section>
class="xml-element"></Paper>