<?xml version="1.0" standalone="yes"?>
<Paper uid="E95-1016">
  <Title>On Learning more Appropriate Selectional Restrictions</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> We present some variations affecting the association measure and thresholding on a technique for learning Selectional Restrictions from on-line corpora. It uses a wide-coverage noun taxonomy and a statistical measure to generalize the appropriate semantic classes. Evaluation measures for the Selectional Restrictions learning task are discussed. Finally, an experimental evaluation of these variations is reported.</Paragraph>
    <Paragraph position="1"> Subject Areas: corpus-based language modeling, computational lexicography</Paragraph>
  </Section>
class="xml-element"></Paper>