<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2237">
  <Title>Using Chunk Based Partial Parsing of Spontaneous Speech in Unrestricted Domains for Reducing Word Error Rate in Speech Recognition</Title>
  <Section position="13" start_page="1458" end_page="1458" type="concl">
    <SectionTitle>
9 Summary
</SectionTitle>
    <Paragraph position="0"> In this paper we have shown that it is feasible to produce chunk based representations for spontaneous speech in unrestricted domains with a high level of accuracy.</Paragraph>
    <Paragraph position="1"> The chunk representations are used to generate scores for an Nbest list reranking component.</Paragraph>
    <Paragraph position="2"> The results are promising, in that the best performance on a randomly selected test set is an absolute decrease in word error rate of 0.3 percent, measured on the new first hypotheses in the reranked Nbest lists.</Paragraph>
  </Section>
class="xml-element"></Paper>