<?xml version="1.0" standalone="yes"?>
<Paper uid="C86-1111">
  <Title>A New Predictive Analyzer of English</Title>
  <Section position="5" start_page="471" end_page="471" type="concl">
    <SectionTitle>
4. Conclusion
</SectionTitle>
    <Paragraph position="0"> Based on the observation of human recognition process of English sentences of a non-native speaker, predictions we make during file process are analyzed. We have also presented a description method of such predictions as grammar rules which is based on Greibach normal form, mad recognition mechanisms that are specified by these rules, realized by using three stacks: the prediction stack, the and stack, and the NP stack. The extension of the rule description and introduction of these stacks provide us with a simple yet powerful means for recognition of syntactic structures.</Paragraph>
    <Paragraph position="1"> An experimental analysis of more than 150 sentences is carried out, and necessary length of lookahead and preference factors as well as the plausibility of the above mechanisms are tested.</Paragraph>
    <Paragraph position="2"> Over 70 percent of the sentences are recognized as desired and looking two words ahead seems to be the critical length for the predictive recognition.</Paragraph>
  </Section>
class="xml-element"></Paper>