<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1315">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics Empirical Verification of Adjacency Pairs Using Dialogue Segmentation</Title>
  <Section position="9" start_page="105" end_page="105" type="evalu">
    <SectionTitle>
5 Results for kh
</SectionTitle>
    <Paragraph position="0"> Here are the 25 pairs with the highest kh  scores.</Paragraph>
    <Paragraph position="1"> With tail probability p = .0001, a kh  normalises the list; low-frequency acts like REJECT and EXPLAINED_REJECT now appear as a part of their respective pairs. These results give empirical justification for Sacks and Schegloff's adjacency pairs, and reveals more not mentioned elsewhere in the literature, such as DEFER:ACCEPT. As such, it gives a good idea of what kinds of speech acts are expected within a chunk.</Paragraph>
    <Paragraph position="2"> In addition, these results can be plotted into a directed acyclic graph (seen in Figure 1). This graph can be used as a sort of conversational map.</Paragraph>
  </Section>
class="xml-element"></Paper>