<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1025">
  <Title>Named Entity Recognition: A Maximum Entropy Approach Using Global Information</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have shown that the maximum entropy framework is able to use global information directly. This enables us to build a high performance NER without using separate classifiers to take care of global consistency or complex formulation on smoothing and backoff models (Bikel et al., 1997). Using less training data than other systems, our NER is able to perform as well as other state-of-the-art NERs.</Paragraph>
    <Paragraph position="1"> Information from a sentence is sometimes insufficient to classify a name correctly. Global context from the whole document is available and can be exploited in a natural manner with a maximum entropy classifier. We believe that the underlying principles of the maximum entropy framework are suitable for exploiting information from diverse sources. Borthwick (1999) successfully made use of other hand-coded systems as input for his MENE system, and achieved excellent results. However, such an approach requires a number of hand-coded systems, which may not be available in languages other than English. We believe that global context is useful in most languages, as it is a natural tendency for authors to use abbreviations on entities already mentioned previously.</Paragraph>
  </Section>
class="xml-element"></Paper>