<?xml version="1.0" standalone="yes"?>
<Paper uid="P02-1061">
  <Title>Teaching a Weaker Classifier: Named Entity Recognition on Upper Case Text</Title>
  <Section position="8" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we have shown that the performance of NERs on upper case text can be improved by using a mixed case NER with unlabeled text. Named entity recognition on mixed case text is easier than on upper case text, where case information is unavailable. By using the teaching process, we can reduce the performance gap between mixed and upper case NER by as much as 39% for MUC-6 and 22% for MUC-7. This approach can be used to improve the performance of NERs on speech recognition output, or even for other tasks such as part-of-speech tagging, where case information is helpful. With the abundance of unlabeled text available, such an approach requires no additional annotation effort, and hence is easily applicable.</Paragraph>
    <Paragraph position="1"> This way of teaching a weaker classifier can also be used in other domains, where the task is to infer a86 a87 a88 , and an abundance of unlabeled data  classifier a4 a86 a40 a16 a11 a87 a88 such that a16 provides additional &amp;quot;useful&amp;quot; information that can be utilized by this second classifier, then one can use this second classifier to automatically tag the unlabeled data a80 , and select from a80 examples that can be used to supplement the training data for training a86a93a87a94a88 .</Paragraph>
  </Section>
class="xml-element"></Paper>