<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2097">
  <Title>Compiling Language Models from a Linguistically Motivated Unification Grammar</Title>
  <Section position="7" start_page="675" end_page="675" type="concl">
    <SectionTitle>
6 Conclusions and Further
</SectionTitle>
    <Paragraph position="0"> Directions j We found the results presented above surprising and interesting. When we 1)egal: our programme of attempting to compile increasingly larger linguistically based unification grammars into language models, we had expected to see a steady combinatorial increase, which we guessed would be most obviously related to complex clause structure. This did not turn out to be the case. Instead, the serious problems we encountered were caused by a small number of critical rules, of which the one for relative clause modification was by the far the worst. It was not immediately obvious how to deal with the problem, but a careful analysis revealed a reasonable con:promise solution, whose only drawback was a significant but undisastrous degradation in recognition speed.</Paragraph>
    <Paragraph position="1"> It seems optimistic to hope that the relative clause problem is the end of the story; the obvious way to investigate is by continuing to expand the gramlnar in the same incremental fashion, and find out what happens next. We intend to do this over the next few months, and expect in due course to be able to l)resent further results.</Paragraph>
  </Section>
class="xml-element"></Paper>