<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-1063">
  <Title>Discriminative Syntactic Language Modeling for Speech Recognition</Title>
  <Section position="7" start_page="512" end_page="513" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> The results presented in this paper are a first step in examining the potential utility of syntactic features for discriminative language modeling for speech recognition. We tried two possible sets of features derived from the full annotation, as well as a variety of possible feature sets derived from shallow parse and POS tag sequences, the best of which gave a small but significant improvement beyond what was provided by the n-gram features. Future work will include a further investigation of parserderived features. In addition, we plan to explore the alternative parameter estimation methods described in (Roark et al., 2004a; Roark et al., 2004b), which were shown in this previous work to give further improvements over the perceptron.</Paragraph>
    <Paragraph position="1"> 5We use the Matched Pair Sentence Segment test for WER, a standard measure of significance, to calculate this p-value.</Paragraph>
  </Section>
class="xml-element"></Paper>