<?xml version="1.0" standalone="yes"?>
<Paper uid="W99-0314">
  <Title>Automatically Extracting</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Automatically Extracting
Abstract
</SectionTitle>
    <Paragraph position="0"> This paper describes how to automatically extract grounding features and segment a dialogue into discourse units, once the dialogue has been annotated with the DR/ backward- and forward-looking tags. Such an approach eliminates the need for separate annotation of grounding, making dialogue annotation quicker and removing a possible source of error. A preliminary test of the mapping against a human annotator is presented.</Paragraph>
  </Section>
class="xml-element"></Paper>