<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1026">
  <Title>Learning the Structure of Task-driven Human-Human Dialogs</Title>
  <Section position="2" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> Data-driven techniques have been used for many computational linguistics tasks.</Paragraph>
    <Paragraph position="1"> Models derived from data are generally more robust than hand-crafted systems since they better re ect the distribution of the phenomena being modeled. With the availability of large corpora of spoken dialog, dialog management is now reaping the bene ts of data-driven techniques. In this paper, we compare two approaches to modeling subtask structure in dialog: a chunk-based model of subdialog sequences, and a parse-based, or hierarchical, model. We evaluate these models using customer agent dialogs from a catalog service domain.</Paragraph>
  </Section>
class="xml-element"></Paper>