<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1007">
  <Title>Exploiting a Probabilistic Hierarchical Model for Generation</Title>
  <Section position="8" start_page="47" end_page="47" type="concl">
    <SectionTitle>
6 Conclusion and Outlook
</SectionTitle>
    <Paragraph position="0"> We have presented empirical evidence that using a tree model in addition to a language model can improve stochastic NLG.</Paragraph>
    <Paragraph position="1"> FERGUS aS presented in this paper is not ready to be used as a module in applications.</Paragraph>
    <Paragraph position="2"> Specifically, we will add a morphological component, a component that handles flmction words (auxiliaries, determiners), and a component that handles imnctuation. In all three cases, we will provide both knowledge-based and stochastic components, with the aim of comparing their behaviors, and using one type as a back-up tbr the other type. Finally, we will explore FI;R-OUS when applied to a language tbr which a much more limited XTAG grammar is available (for example, specit\[ying only the basic sentence word order as, sw, SVO, and speci(ying subject-verb agreement). In the long run, we intend FEI/OUS to become a flexible system which will use hand-crafted knowledge as much as possible and stochastic models as much as necessary.</Paragraph>
  </Section>
class="xml-element"></Paper>