<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2416">
  <Title>Semantic Role Labeling by Tagging Syntactic Chunks</Title>
  <Section position="5" start_page="0" end_page="0" type="concl">
    <SectionTitle>
4 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have described a semantic role chunker using SVMs.</Paragraph>
    <Paragraph position="1"> The chunking method has been based on a chunked sentence structure at both syntactic and semantic levels. We have jointly performed semantic chunk segmentation and labeling using a set of one-vs-all SVM classifiers on a phrase-by-phrase basis. It has been argued that the new representation has several advantages as compared to the original representation. It yields a semantic role labeler that classifies larger units, exploits relatively larger context, uses less data (possibly, redundant and noisy data are filtered out), runs faster and performs better.</Paragraph>
  </Section>
class="xml-element"></Paper>