<?xml version="1.0" standalone="yes"?>
<Paper uid="A94-1041">
  <Title>Representing Knowledge for Planning Multisentential Text</Title>
  <Section position="5" start_page="203" end_page="203" type="concl">
    <SectionTitle>
5. Conclusion
</SectionTitle>
    <Paragraph position="0"> The distinction between deep and surface structure of the text allows the system to generate relevant letters from an argumentative point of view.</Paragraph>
    <Paragraph position="1"> Besides, letters may deal with a rather large number of various topics (payment of lost or damaged items, etc.). Our concern was therefore to factor the information as much as possible, in other words we wanted to make certain pieces of knowledge portable. For that purpose, it is interesting here to remind the distinction between domain knowledge and domain communicative knowledge (DCK) proposed in (Kittredge and al., 1991).</Paragraph>
    <Paragraph position="2"> For example a police crime report and a detective novel can use the same domain knowledge but the DCK is quite different. We think that it is preferable to call this knowledge &amp;quot;Style Dependent Knowledge&amp;quot;, because two detective novels in two different &amp;quot;domains&amp;quot; (for example a political murder and a crime of passion) could have the same style.</Paragraph>
    <Paragraph position="3"> In our system, conceptual rules are clearly domaindependent. The communicative knowledge used by the rhetoric module to compute the surface structure of the text is style-dependent but it is domain-portable.</Paragraph>
  </Section>
class="xml-element"></Paper>