<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1016">
  <Title>Modeling Commonality among Related Classes in Relation Extraction</Title>
  <Section position="8" start_page="127" end_page="127" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper proposes a novel hierarchical learning strategy to deal with the data sparseness problem in relation extraction by modeling the commonality among related classes. For each class in a class hierarchy, a linear discriminative function is determined in a top-down way using the perceptron algorithm with the lower-level weight vector derived from the upper-level weight vector. In this way, the upper-level discriminative function can effectively guide the lower-level discriminative function learning. Evaluation on the ACE RDC 2003 corpus shows that the hierarchical strategy performs much better than the flat strategy in resolving the critical data sparseness problem in relation extraction.</Paragraph>
    <Paragraph position="1"> In the future work, we will explore the hierarchical learning strategy using other machine learning approaches besides online classifier learning approaches such as the simple perceptron algorithm applied in this paper. Moreover, just as indicated in Figure 2, most relation sub-types in the ACE RDC 2003 corpus (arguably the largest annotated corpus in relation extraction) suffer from the lack of training examples. Therefore, a critical research in relation extraction is how to rely on semi-supervised learning approaches (e.g. bootstrap) to alleviate its dependency on a large amount of annotated training examples and achieve better and steadier performance. Finally, our current work is done when NER has been perfectly done. Therefore, it would be interesting to see how imperfect NER affects the performance in relation extraction.</Paragraph>
    <Paragraph position="2"> This will be done by integrating the relation extraction system with our previously developed NER system as described in Zhou and Su (2002).</Paragraph>
  </Section>
class="xml-element"></Paper>