<?xml version="1.0" standalone="yes"?>
<Paper uid="P92-1019">
  <Title>A CONNECTIONIST PARSER FOR STRUCTURE UNIFICATION GRAMMAR</Title>
  <Section position="9" start_page="150" end_page="150" type="concl">
    <SectionTitle>
CONCLUSION
</SectionTitle>
    <Paragraph position="0"> This paper has given an overview of a connectionist syntactic constituent structure parser which uses Structure Unification Grammar as its grammatical framework. The connectionist computational architecture which is used stores and dynamically manipulates symbolic representations, thus making it ideally suited for syntactic parsing.</Paragraph>
    <Paragraph position="1"> However, the architecture's inability to represent arbitrary disjunction and its bounded memory capacity pose problems for parsing. These difficulties can be overcome by using Structure Unification Grammar as the grammatical framework, due to SUG's extensive use of partial descriptions.</Paragraph>
    <Paragraph position="2"> This investigation has indeed led to insights into efficient natural language parsing. This parser's speed is independent of the size of its grammar. It only uses a bounded amount of memory. Its output is incremental, monotonic, and does not include disjunction. Its disambiguation of the signal generation box in figure 6. For all such rules, the identity of one of the nodes can be determined uniquely given the other node and the parser state. For example in the dominance instantiating operation, given the unparented node, the host of that node can be found because host is a function. This constraint on parser operations seems to have significant linguistic import, but more investigation of this possibility is necessary.</Paragraph>
    <Paragraph position="3"> 4In the current simulation of the parser implementation the arbitrators are controlled by the user. mechanism provides a parallel interface for the influence of higher level language modules. Assuming neurologically plausible timing characteristics for the computing units of the connectionist architecture, the parser's speed is roughly compatible with the speed of human speech. In the future the ability of this architecture to do evidential reasoning should allow the use of statistical information in the parser, thus making use of both grammatical and statistical approaches to language in a single framework.</Paragraph>
  </Section>
class="xml-element"></Paper>