<?xml version="1.0" standalone="yes"?>
<Paper uid="J03-3005">
  <Title>Using the Web to Obtain Frequencies for Unseen Bigrams</Title>
  <Section position="6" start_page="482" end_page="482" type="ackno">
    <SectionTitle>
Acknowledgments
</SectionTitle>
    <Paragraph position="0"> This work was conducted while both authors were at the Department of Computational Linguistics, Saarland University, Saarbr &amp;quot;ucken. The work was inspired by a talk that Gregory Grefenstette gave in Saarbr &amp;quot;ucken in 2001 about his research on using the Web as a corpus. The present article is an extended and revised version of Keller, Lapata, and Ourioupina (2002). Stephen Clark and Stefan Riezler provided valuable comments on this research. We are also grateful to four anonymous reviewers for Computational Linguistics; their feedback helped to substantially improve the present article.</Paragraph>
    <Paragraph position="1"> Special thanks are due to Stephen Clark and Detlef Prescher for making their pseudodisambiguation data sets available.</Paragraph>
  </Section>
class="xml-element"></Paper>