<?xml version="1.0" standalone="yes"?>
<Paper uid="W90-0103">
  <Title>A Connectionist Treatment of Grammar for Generation: Relying on Emergents</Title>
  <Section position="10" start_page="21" end_page="21" type="concl">
    <SectionTitle>
9 Summary
</SectionTitle>
    <Paragraph position="0"> I have proposed a new way to handle syntax for generation. The proposal also relies heavily on parallelism: part-wise parallelism, competition, and cooperation. Also, syntactic considerations are used in parallel with lexical and world knowledge and there is pervasive interaction among them. This promises improved output quality without sacriricing speed, on parallel hardware. The proposal also relies heavily on emergents -- it does not make syntactic choices nor build up representations of syntactic structure. The network representations of linguistic knowledge affect word choice and order directly.</Paragraph>
    <Paragraph position="1"> This work is not traditional linguistics, artiricial intelligence, or connectionism, but uses techniques from all three fields. I hope this will stimulate further work in empirical computational linguistics, modeling human language production, and building useful parallel generation systems.</Paragraph>
  </Section>
class="xml-element"></Paper>