<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2421">
  <Title>Semantic Role Labeling Via Generalized Inference Over Classifiers</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> We show that linguistic information is useful for semantic role labeling used both to derive features and to derive hard constraints on the output. We show that it is possible to use integer linear programming to perform inference that incorporates a wide variety of hard constraints that would be difficult to incorporate using existing methods.</Paragraph>
    <Paragraph position="1"> In addition, we provide further evidence supporting the use of scoring phrases over scoring phrase boundaries for complex tasks.</Paragraph>
    <Paragraph position="2"> Acknowledgments This research is supported by NSF grants ITR-IIS-0085836, ITR-IIS-0085980 and IIS9984168, EIA-0224453 and an ONR MURI Award. We also thank AMD for their equipment donation and Dash Optimization for free academic use of their Xpress-MP software.</Paragraph>
  </Section>
class="xml-element"></Paper>