<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-0857">
  <Title>Generative Models for Semantic Role Labeling</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The goal in the SENSEVAL-3 semantic role labeling task is to identify roles and optionally constituent boundaries for each role, given a natural language sentence, target, and frame. The Utah approach to this task is to apply machine learning techniques to create a model capable of semantically analyzing unseen sentences. We have developed a set of generative models (Jordan, 1999) that have the advantages of flexibility, power, and ease of applicability for semi-supervised learning scenarios. We can supplement any of the generative models with a constituent classifier that determines, given a sentence and parse, which parse constituents are most likely to correspond to a role. We apply the combination to the &amp;quot;hard,&amp;quot; or restricted version of the role labeling task, in which the system is provided only with the sentence, target, and frame, and must determine which sentence constituents to label with roles.</Paragraph>
    <Paragraph position="1"> We discuss our overall model, the constituent classifier we use in the hard task, and the classifier's use at role-labeling time. We entered four sets of answers, as discussed in Section 5. The first two correspond to the &amp;quot;easy&amp;quot; task, in which the role-bearing constituents - those parts of the sentence corresponding to a role - are provided to the system with the target and frame. The second two are variants for the &amp;quot;hard&amp;quot; task. Finally, we discuss Future Work and conclude the paper.</Paragraph>
  </Section>
class="xml-element"></Paper>