<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2306">
  <Title>Semi-Automatic Generation of Dialogue Applications in the GEMINI Project [?]</Title>
  <Section position="6" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> In the GEMINI project we aim at the design and implementation of an application generation platform, which generates state of the art speech and web applications.</Paragraph>
    <Paragraph position="1"> The platform architecture is open to generate multi-lingual dialogue applications from different databases in several modalities. We can consider the platform a success, as we have streamlined the design process of the applications thanks the help of our assistants. The use of standards (e.g. VoiceXML) places us in a good position in the market of voice applications.</Paragraph>
    <Paragraph position="2"> To facilitate the communication between all modules, an abstract dialogue description language, called GDialogXML, was defined, which is another important result from the project.</Paragraph>
    <Paragraph position="3"> Future work will cover the realisation of the improved AGP, which will allow multi-lingual applications with mixed initiative, overanswering, and user modelling. Additionally a graphical control flow will be available to the designer. Furthermore the AGP will be evaluated against other approaches of dialogue design.</Paragraph>
  </Section>
class="xml-element"></Paper>