<?xml version="1.0" standalone="yes"?>
<Paper uid="N03-1013">
  <Title>A Categorial Variation Database for English</Title>
  <Section position="8" start_page="0" end_page="0" type="ackno">
    <SectionTitle>
Acknowledgments
</SectionTitle>
    <Paragraph position="0"> This work has been supported, in part, by ONR MURI Contract FCPO.810548265, Mitre Contract 0104187712, and NSF CISE Research Infrastructure Award EIA0130422. We would like to thank all the annotators who participated in the evaluation of the database.</Paragraph>
    <Paragraph position="1"> viewed as a weak link in our comparison since it does not provide a deep analysis as would be produced by morphological analysis systems. However, we have found that most morphological analyzers, including ones with large-scale coverage such as the Xtag system (Karp et al., 1992), address inflectional--not derivational--morphology; thus, their basis for comparison is even weaker than would be provided by the Porter stemmer.</Paragraph>
    <Paragraph position="2"> 11This is, in fact, the approach used in the HeadGen and DUSTer applications described above.</Paragraph>
  </Section>
class="xml-element"></Paper>