<?xml version="1.0" standalone="yes"?>
<Paper uid="N04-1038">
  <Title>Unsupervised Learning of Contextual Role Knowledge for Coreference Resolution</Title>
  <Section position="8" start_page="9" end_page="9" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> The goal of our research was to explore the use of contextual role knowledge for coreference resolution. We identified three ways that contextual roles can be exploited: (1) by identifying caseframes that co-occur in resolutions, (2) by identifying nouns that co-occur with case-frames and using them to cross-check anaphor/candidate compatibility, (3) by identifying semantic classes that co-occur with caseframes and using them to cross-check anaphor/candidate compatability. We combined evidence from four contextual role knowledge sources with evidence from seven general knowledge sources using a Dempster-Shafer probabilistic model.</Paragraph>
    <Paragraph position="1"> Our coreference resolver performed well in two domains, and experiments showed that each contextual role knowledge source contributed valuable information. We found that contextual role knowledge was more beneficial for pronouns than for definite noun phrases. This suggests that different types of anaphora may warrant different treatment: definite NP resolution may depend more on lexical semantics, while pronoun resolution may depend more on contextual semantics. In future work, we plan to follow-up on this approach and investigate other ways that contextual role knowledge can be used.</Paragraph>
  </Section>
class="xml-element"></Paper>