<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0623">
  <Title>A Joint Model for Semantic Role Labeling</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> It is evident that there are strong statistical patterns in the syntactic realization and ordering of the arguments of verbs; for instance, if an active predicate has an A0 argument it is very likely to come before anA1argument. Our model aims to capture such dependencies among the labels of nodes in a syntactic parse tree.</Paragraph>
    <Paragraph position="1"> However, building such a model is computationally expensive. Since the space of possible joint labelings is exponential in the number of parse tree nodes, a model cannot exhaustively consider these labelings unless it makes strong independence assumptions. To overcome this problem, we adopt a discriminative re-ranking approach reminiscent of (Collins, 2000). We use a local model, which labels arguments independently, to generate a smaller number of likely joint labelings. These candidate labelings are in turn input to a joint model which can use global features and re-score the candidates. Both the local and global re-ranking models are log-linear (maximum entropy) models.</Paragraph>
    <Paragraph position="2"> In the following sections, we briefly describe our local and joint models and the system architecture for combining them. We list the features used by our models, with an emphasis on new features, and compare the performance of a local and a joint model on the CoNLL shared task. We also study an approach to increasing the robustness of the semantic role labeling system to syntactic parser errors, by considering multiple parse trees generated by a statistical parser.</Paragraph>
  </Section>
class="xml-element"></Paper>