<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-0434">
  <Title>A Robust Risk Minimization based Named Entity Recognition System</Title>
  <Section position="5" start_page="0" end_page="0" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we presented a general token-based NLP tagging system using a robust risk minimization classification method. The system can take advantage of different kinds of linguistic features.</Paragraph>
    <Paragraph position="1"> We have studied the impact of various local linguistic features on the performance of our system. It is interesting to note that most performance improvement can be achieved with some relatively simple token features that are easy to construct. Although more sophisticated linguistic features will also be helpful, they provide much less improvement than might be expected. This observation supports the view that language independent named entity recognition systems can, with relatively small effort, achieve competitive levels of accuracy.</Paragraph>
  </Section>
class="xml-element"></Paper>