<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-2007">
  <Title>Semi-supervised Relation Extraction with Label Propagation</Title>
  <Section position="5" start_page="27" end_page="27" type="concl">
    <SectionTitle>
4 Conclusion and Future work
</SectionTitle>
    <Paragraph position="0"> This paper approaches the task of semi-supervised relation extraction on Label Propagation algorithm.</Paragraph>
    <Paragraph position="1"> Our results demonstrate that, when only very few labeled examples are available, this manifold learning based algorithm can achieve better performance than supervised learning method (SVM) and bootstrapping based method, which can contribute to 3LIBSVM: a library for support vector machines. Software available at http://www.csie.ntu.edu.tw/[?]cjlin/libsvm. minimize corpus annotation requirement. In the future we would like to investigate how to select more useful feature stream and whether feature selection method can improve the performance of our graph-based semi-supervised relation extraction.</Paragraph>
  </Section>
class="xml-element"></Paper>