<?xml version="1.0" standalone="yes"?>
<Paper uid="N01-1016">
  <Title>Edit Detection and Parsing for Transcribed Speech</Title>
  <Section position="6" start_page="6" end_page="6" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have presented a simple architecture for parsing transcribed speech in which an edited word detector is rst used to remove such words from the sentence string, and then a statistical parser trained on edited speech (with the edited nodes removed) is used to parse the text. The edit detector reduces the misclassi cation rate on edited words from the null-model (marking everything as not edited) rate of 5.9% to 2.2%.</Paragraph>
    <Paragraph position="1"> To evaluate our parsing results we have introduced a new evaluation metric, relaxed edited labeled precision/recall. The purpose of this metric is to make evaluation of a parse tree relatively indi erent to the exact tree position of EDITED nodes, in much the same way that the previous metric, relaxed labeled precision/recall, make it indi erent to the attachment of punctuation. By this metric the parser achieved 85.3% precision and 86.5% recall.</Paragraph>
    <Paragraph position="2"> There is, of course, great room for improvement, both in stand-alone edit detectors, and their combination with parsers. Also of interest are models that compute the joint probabilities of the edit detection and parsing decisions | that is, do both in a single integrated statistical process.</Paragraph>
  </Section>
class="xml-element"></Paper>