<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-1814">
  <Title>Extracting Pronunciation-translated Names from Chinese Texts using Bootstrapping Approach</Title>
  <Section position="5" start_page="11" end_page="11" type="concl">
    <SectionTitle>
5 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> The presence of P-Names brings more ambiguities to Chinese word segmentation and general Chinese named entity recognition. However, there is a dearth of annotated corpus for extracting and classifying P-Names. To cope with the problem of sparse training resources, this paper presents a bootstrapping module to identify P-Names and classify them into parts of named entitites if possible. The PN-Finder could also contribute to general Chinese named entity recognition and achieve promising performance on the MET-2 test corpus.</Paragraph>
    <Paragraph position="1"> Currently, we use only a single word as the context, more context could be considered in the future research. We also aim to extend this method to extract organization names from Chinese documents obtained from the Internet.</Paragraph>
  </Section>
class="xml-element"></Paper>