<?xml version="1.0" standalone="yes"?>
<Paper uid="E95-1012">
  <Title>Stochastic HPSG</Title>
  <Section position="8" start_page="88" end_page="88" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have presented two proposals for the association of probabilities with typed feature-structures of the form used in HPSG. As far as we know these are the most detailed of their type, and the ones which are most likely to be able to exploit standard training and parsing algorithms. For typed feature structures lacking re-entrancy we believe our proposal to be the simplest and most natural which is available. The proposal for dealing with re-entrancy is less satisfactory but offers a basis for empirical exploration, and has definite advantages over the straightforward use of PCFGs. We plan to follow up the current work by training and testing a suitable instantiation of our framework against manually annotated corpora.</Paragraph>
  </Section>
class="xml-element"></Paper>