<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0610">
  <Title>Using Uneven Margins SVM and Perceptron for Information Extraction</Title>
  <Section position="7" start_page="77" end_page="78" type="ackno">
    <SectionTitle>
Acknowledgements
</SectionTitle>
    <Paragraph position="0"> This work is supported by the EU-funded SEKT project (http://www.sekt-project.org).</Paragraph>
    <Paragraph position="1">  small training sets: macro-averaged F1(%) on the two datasets CoNLL-2003 (development set) and Jobs. The uneven margins SVM (t = 0.4) is compared to the standard SVM model with even margins (t = 1). The standard deviations are presented for results on the Jobs dataset.</Paragraph>
  </Section>
class="xml-element"></Paper>