<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-1010">
  <Title>A Plethora of Methods for Learning English Countability</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> This paper compares a range of methods for classifying words based on linguistic diagnostics, focusing on the task of learning countabilities for English nouns.</Paragraph>
    <Paragraph position="1"> We propose two basic approaches to feature representation: distribution-based representation, which simply looks at the distribution of features in the corpus data, and agreement-based representation which analyses the level of token-wise agreement between multiple pre-processor systems. We additionally compare a single multiclass classifier architecture with a suite of binary classifiers, and combine analyses from multiple preprocessors. Finally, we present and evaluate a feature selection method.</Paragraph>
  </Section>
class="xml-element"></Paper>