<?xml version="1.0" standalone="yes"?>
<Paper uid="N04-1037">
  <Title>The (Non)Utility of Predicate-Argument Frequencies for Pronoun Interpretation</Title>
  <Section position="9" start_page="0" end_page="0" type="concl">
    <SectionTitle>
8 Conclusion
</SectionTitle>
    <Paragraph position="0"> In conclusion, our experimental results and error analysis suggest that predicate-argument statistics offer little predictive power to a pronoun interpretation system trained on a state-of-the-art set of morphosyntactic features. On the one hand, it appears that the distribution of pronouns in discourse allows for a system to correctly resolve a majority of them using only morphosyntactic cues. On the other hand, predicate-argument statistics appear to provide a poor substitute for the world knowledge that may be necessary to correctly interpret the remaining cases.</Paragraph>
  </Section>
class="xml-element"></Paper>