<?xml version="1.0" standalone="yes"?>
<Paper uid="I05-2007">
  <Title>A resource-based Korean morphological annotation system</Title>
  <Section position="6" start_page="40" end_page="41" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> We experimented with a method likely to enhance the performances of state-of-the-art systems of Korean morphological annotation. We made language resources the central point of the problem. All complex operations were integrated among resource management operations.</Paragraph>
    <Paragraph position="1"> The output of our system is accurate and informative; the language resources used by the system can be easily updated, which allows users to control the evolution of the performances of the system. Morphological annotation of Korean text is performed directly with a lexicon of words and without morphological rules, which simplifies and speeds up the process.</Paragraph>
    <Paragraph position="2"> This work opens several perspectives. The resources will be extended by running the annotator and analysing output. Existing approaches  to the analysis of unrecognised morphemes could be combined to our system: such approaches are complementary to our resource-based approach, and would take advantage of the rich information provided on the neighbouring words. Ambiguity resolution techniques can be applied to the output of our annotator: the syntactic approach would take advantage of the rich linguistic information provided in output; classical statistical approaches and priority rules (Kang, 1999) are applicable as well. Finally, a parallel system is under construction for Finnish, another agglutinative language with undelimited morphemes.</Paragraph>
  </Section>
class="xml-element"></Paper>