<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1087">
  <Title>A Connectionist Architecture for Learning to Parse</Title>
  <Section position="7" start_page="536" end_page="536" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper demonstrates for the first time that a connectionist network can learn syntactic parsing.</Paragraph>
    <Paragraph position="1"> This improvement is the result of extending a standard architecture (Simple Recurrent Networks) with a technique for representing linguistic constituents (Temporal Synchrony Variable Binding). This extension allows Simple Synchrony Networks to generalize what they learn across constituents, thereby solving the sparse data problems of previous connectionist architectures. Initial experiments have empirically demonstrated this ability, and future extensions are likely to significantly improve on these results. We believe that the combination of this generalization ability with the adaptability of connectionist networks holds great promise for many areas of Computational Linguistics.</Paragraph>
  </Section>
class="xml-element"></Paper>