<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-2010">
  <Title>Named Entity Recognition as a House of Cards: Classifier Stacking</Title>
  <Section position="5" start_page="70" end_page="70" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> In conclusion, we have presented a classifier stacking method which uses transformation-based learning to obtain a course-grained initial entity annotation, then applies Snow to improve the classification on samples where there is strong feature interaction and, finally, uses a forward-backward algorithm to compute a global-best entity type assignment. By using the pipelined processing, this method improves the performance substantially when compared with the original algorithms (fnTBL, Snow+fnTBL).</Paragraph>
  </Section>
class="xml-element"></Paper>