<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1006">
  <Title>Attention Shifting for Parsing Speech [?]</Title>
  <Section position="5" start_page="8" end_page="8" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> We presented a parsing technique that shifts the attention of a word-lattice parser in order to ensure syntactic analyses for all lattice paths. Attention shifting can be thought of as a meta-process around the first stage of a multi-stage word-lattice parser.</Paragraph>
    <Paragraph position="1"> We show that this technique reduces the amount of work exerted by the first stage PCFG parser while maintaining comparable language modeling performance. null Attention shifting is a simple technique that attempts to make word-lattice parsing more efficient. As suggested by the results for the acoustic lattice experiments, this technique alone is not sufficient.</Paragraph>
    <Paragraph position="2"> Solutions to improve these results include modifying the first-stage grammar by annotating the category labels with local syntactic features as suggested in (Johnson, 1998) and (Klein and Manning, 2003) as well as incorporating some level of lexicalization. Improving the quality of the parses selected by the first stage should reduce the need for generating such a large number of candidates prior to pruning, improving efficiency as well as overall accuracy. We believe that attention shifting, or some variety of this technique, will be an integral part of efficient solutions for word-lattice parsing.</Paragraph>
  </Section>
class="xml-element"></Paper>