<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-1073">
  <Title>Joint Learning Improves Semantic Role Labeling</Title>
  <Section position="8" start_page="595" end_page="595" type="concl">
    <SectionTitle>
7 Conclusions
</SectionTitle>
    <Paragraph position="0"> Reflecting linguistic intuition and in line with current work, we have shown that there are substantial gains to be had by jointly modeling the argument frames of verbs. This is especially true when we model the dependencies with discriminative models capable of incorporating long-distance features.</Paragraph>
  </Section>
class="xml-element"></Paper>