<?xml version="1.0" standalone="yes"?>
<Paper uid="W01-1006">
  <Title>Semi-Automatic Practical Ontology Construction by Using a Thesaurus, Computational Dictionaries, and Large Corpora</Title>
  <Section position="7" start_page="3" end_page="3" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper we have proposed a semi-automatic construction method of the LIP ontology and an  ontology includes substantial semantic relations between concepts, and differs from many of the resources in that there is no language-dependent knowledge in the resource, which is a network of concepts, not words. Semantic relations of the LIP ontology are generated by considering two different languages, Korean and Japanese. In addition, we can easily apply the ontology without additional lexicographic works, since large-scale bilingual dictionaries have words already annotated with concept codes of the LIP ontology. Therefore, our LIP ontology is a language independent and practical knowledge base. You can apply this ontology for other languages, if one merely inserts Kadokawa concept codes for each entry into the dictionary. Our ontology construction method requires manual processing, i.e., mapping from syntactic relations to semantic relations by specific rules and human intuition. However, this is necessary for building a high-quality semantic knowledge base. Our construction method is quite effective in comparison with other methods.</Paragraph>
    <Paragraph position="1"> We plan further research on how to effectively divide the grain size of ontology concepts to best express the whole world knowledge, and how to utilize the LIP ontology in a full semantic analysis process.</Paragraph>
  </Section>
class="xml-element"></Paper>