<?xml version="1.0" standalone="yes"?>
<Paper uid="P99-1018">
  <Title>Ordering Among Premodifiers</Title>
  <Section position="7" start_page="141" end_page="141" type="concl">
    <SectionTitle>
7 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> We have presented three techniques for exploring prior corpus evidence in predicting the order of premodifiers within noun phrases. Our methods expand on observable data, by inferring new relationships between premodifiers even for combinations of premodifiers that do not occur in the training corpus. We have empirically validated our approach, showing that we can predict order with more than 94% accuracy when enough corpus data is available. We have also implemented our procedure in a text generator, producing more fluent output sentences.</Paragraph>
    <Paragraph position="1"> We are currently exploring alternative ways to integrate the classes constructed by the third stage of our system into our generator. In the future, we will experiment with semantic (rather than positional) clustering of premoditiers, using techniques such as those proposed in \[Hatzivassiloglou and McKeown 1993; Pereira et al. 1993\]. The qualitative analysis of the output of our clustering module shows that frequently positional and semantic classes overlap, and we are interested in measuring the extent of this phenomenon quantitatively. Conditioning the premodifier ordering on the head noun is another promising approach, at least for very frequent nouns.</Paragraph>
  </Section>
class="xml-element"></Paper>