<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-2194">
  <Title>A Gradual Refinement Model for A Robust Thai Morphological Analyzer</Title>
  <Section position="5" start_page="1088" end_page="1088" type="concl">
    <SectionTitle>
6. Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> This paper has described a new simple technique that performs the disambiguation of word boundary, POS tagging and implicit spelling correction by using local information such as lexicon preference, a consecutive POS preference and semantic dependency strength measurement of the associative words in a sentence. From the experimentation results, while a corpus based approach has proven to be efficient, the method seems to be computationally costly and requires a large amount of training data and validation data. For the proposed model, it can work in time efficient and increase the accuracy of word boundary and tagging disambiguation as well as implicit spelling error.</Paragraph>
    <Paragraph position="1"> The further directions for this research will concern with unknown word processing and increase the accuracy of the gradual refinement method.</Paragraph>
  </Section>
class="xml-element"></Paper>