<?xml version="1.0" standalone="yes"?>
<Paper uid="N04-1015">
  <Title>Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> We consider the problem of modeling the content structure of texts within a specific domain, in terms of the topics the texts address and the order in which these topics appear.</Paragraph>
    <Paragraph position="1"> We first present an effective knowledge-lean method for learning content models from un-annotated documents, utilizing a novel adaptation of algorithms for Hidden Markov Models. We then apply our method to two complementary tasks: information ordering and extractive summarization. Our experiments show that incorporating content models in these applications yields substantial improvement over previously-proposed methods.</Paragraph>
  </Section>
class="xml-element"></Paper>