<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1433">
  <Title>Rhetorical structure in dialog*</Title>
  <Section position="5" start_page="250" end_page="250" type="relat">
    <SectionTitle>
5 Related Work
</SectionTitle>
    <Paragraph position="0"> In recent years there has been much research on annotation schemes for dialog. Traum and Hinkelman outline four levels of &amp;quot;conversational acts&amp;quot; in (1992). &amp;quot;Argumentation acts&amp;quot;, including rhetorical relations, form the top level, but this level is not described in detail. DAMSL (Core and Allen, 1997) includes speech acts and some grounding acts, but not rhetorical relations. The HCRC Maptask project annotation scheme includes adjacency pairs, but not rhetorical relations (Carletta et al., 1996).</Paragraph>
    <Paragraph position="1"> The COCONUT project annotation manual allows the annotator to mark individual utterances as elaboration, and segments as summary, act:condition, act:consequence or otherinfo (DiEugenio et al., 1998). This annotation scheme does not treat rhetorical structure separately from other types of dialog behavior. We have observed enough structure in the corpora we have looked at to justify treating rhetorical structure as a separate, important phenomenon. For instance, in a DAMSLtagged set of 8 dialogs in our corpus, 40% of the utterances were statements, and many of these appeared in sequences of statements. The relationships between many of these statements are unclear without a model of rhetorical structure.</Paragraph>
    <Paragraph position="2"> In (1999), Nakatani and Traum describe a hierarchical annotation of dialog for I-units, based on the .. domination and satisfaction-precedence relations of (Grosz and Sidner, 1986). Other researchers have shown that Grosz and Sidner's model of discourse structure (GST) and RST are similar in many respects \[(Moser and Moore, 1996), (Marcu, 1999)\].</Paragraph>
    <Paragraph position="3"> However, RST provides more specific relations than GST, and this is useful for content planning. As well as helping to specify generation goals, content and ordering constraints, the rhetorical information is needed in case the system has to explain what it.</Paragraph>
    <Paragraph position="4"> has said.</Paragraph>
    <Paragraph position="5"> 4A rough draft is available from the author.</Paragraph>
    <Paragraph position="6"> RDA is an annotation scheme for identifying rhetorical structure in explanatory texts in the SHERLOCK domain (Moser et al., 1996). We follow RDA in requiring annotators to consider both intentional and informational relations. However, because of the dialog issues previously described, RDA is not sufficient for dialog.</Paragraph>
    <Paragraph position="7"> Marcu uses discourse-cuesto&amp;quot;automa~ically uncover rhetorical relations in text (1997). Much of this work is applicable to the problem of uncovering rhetorical relations in dialog; however, many cues in dialog are prosodic and it is not yet possible to obtain accurate information about prosodic cues automatically. null</Paragraph>
  </Section>
class="xml-element"></Paper>