<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0628">
  <Title>Semantic Role Labeling as Sequential Tagging</Title>
  <Section position="5" start_page="195" end_page="195" type="concl">
    <SectionTitle>
3 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have presented a simple SRL system submitted to the CoNLL-2005 shared task, which treats the SRL problem as a sequence tagging task (using a BIO tagging scheme). Given the simplicity of the approach, we believe that the results are very good and competitive compared to the stateof-the-art. We also provided a comparison between two SRL systems sharing the same architecture, but build on partial vs. full parsing, respectively. Although the full parsing approach obtains better results and has some implementation advantages, the partial parsing system shows also a quite competitive performance. The results on the development set differ in 2.18 points, but the outputs generated by the two systems are significantly different. The final system, which scored F1=76.59 in the official test set, is a combination of both individual systems aiming at increasing coverage and recall.</Paragraph>
  </Section>
class="xml-element"></Paper>