<?xml version="1.0" standalone="yes"?>
<Paper uid="P92-1006">
  <Title>Parsing*</Title>
  <Section position="7" start_page="45" end_page="46" type="concl">
    <SectionTitle>
6. Conclusions
</SectionTitle>
    <Paragraph position="0"> There are many different applications of natural language parsing, and each application has a different cost threshold for efficiency, robustness, and accuracy. '\['he &amp;quot;Pick), algorithm introduces a framework for integral.ing  these thresholds into the configuration of the parser in order to maximize the effectiveness of the parser for the task at hand. An application which requires a high degree of accuracy would omit the Tree Completion phase of the parser. A real-time application would limit the number of edges generated by the parser, likely at the cost of accuracy. An application which is robust to errors but requires efficient processing of input would omit the Covered Bidirectional phase.</Paragraph>
    <Paragraph position="1"> The :Picky parsing algorithm illustrates how probabilistic modelling of natural language can be used to improve the efficiency, robustness, and accuracy of natural language understanding tools.</Paragraph>
  </Section>
class="xml-element"></Paper>