<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1089">
  <Title>Parsing Parallel Grammatical Representations</Title>
  <Section position="5" start_page="547" end_page="547" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> Multistratal theories of grammar are not often chosen as guidelines for computational linguistics, because of performance and manageability concerns. This project, however, should at least demonstrate that even in a high-level language like Prolog a multistratal parsing model can be made to produce consistent results in a reasonable length of time.</Paragraph>
    <Paragraph position="1"> Furthermore, the project described here does more than simply emulate the output of a standard, monostratal CF-PSG parser; it yields a preference ranking of readings for each string, rather than a single right answer. While the Autolexical model may not now be correct for applications in which speed is of primary concern, it has only begun to be implemented computationally, and any serious attempt at inferencing from natural language input will have to produce similar, graded output (Moran, 1988).</Paragraph>
  </Section>
class="xml-element"></Paper>