<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1085">
  <Title>Identifying Agreement and Disagreement in Conversational Speech: Use of Bayesian Networks to Model Pragmatic Dependencies</Title>
  <Section position="8" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have shown how identification of adjacency pairs can help in designing features representing pragmatic dependencies between agreement and disagreement labels. These features are shown to be informative and to help the classification task, yielding a substantial improvement (1.3% to reach a 86.9% accuracy in three-way classification).</Paragraph>
    <Paragraph position="1"> We also believe that the present work may be useful in other computational pragmatic research focusing on multi-party dialogs, such as dialog act (DA) classification. Most previous work in that area is limited to interaction between two speakers (e.g.</Paragraph>
    <Paragraph position="2"> Switchboard, (Stolcke et al., 2000)). When more than two speakers are involved, the question of who is the addressee of an utterance is crucial, since it generally determines what DAs are relevant after the addressee's last utterance. So, knowledge about adjacency pairs is likely to help DA classification.</Paragraph>
    <Paragraph position="3"> In future work, we plan to extend our inference process to treat speaker ranking (i.e. AP identification) and agreement/disagreement classification as a single, joint inference problem. Contextual information about agreements and disagreements can also provide useful cues regarding who is the addressee of a given utterance. We also plan to incorporate acoustic features to increase the robustness of our procedure in the case where only speech recognition output is available.</Paragraph>
  </Section>
class="xml-element"></Paper>