<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-0109">
  <Title>The Role of Lexical Resources in CJK Natural Language Processing</Title>
  <Section position="11" start_page="123" end_page="123" type="concl">
    <SectionTitle>
7 Conclusions
</SectionTitle>
    <Paragraph position="0"> Performing such tasks as orthographic normalization and named entity extraction accurately is beyond the ability of statistical methods alone, not to speak of C2C conversion and morphological analysis. However, the small-scale lexical resources currently used by many NLP tools are inadequate to these tasks. Because of the irregular orthography of the CJK writing systems, lexical databases fine-tuned to the needs of NLP applications are required. The building of large-scale lexicons based on corpora consisting of even billions of words has come of age. Since lexicon-driven techniques have proven their effectiveness, there is no need to overly rely on probabilistic methods. Comprehensive, up-to-date lexical resources are the key to achieving major enhancements in NLP technology.</Paragraph>
  </Section>
class="xml-element"></Paper>