<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-1010">
  <Title>Exploiting Domain Structure for Named Entity Recognition</Title>
  <Section position="8" start_page="80" end_page="80" type="concl">
    <SectionTitle>
7 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> Named entity recognition is an important problem that can help many text mining and natural language processing tasks such as information extraction and question answering. Currently NER faces a poor domain adaptability problem when the test data is not from the same domain as the training data. We present several strategies to exploit the domain structure in the training data to improve the performance of the learned NER classifier on a new domain. Our results show that the domain-aware strategies we proposed improved the performance over a baseline method that represents the state-of-the-art NER techniques.</Paragraph>
  </Section>
class="xml-element"></Paper>