<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2050">
  <Title>When Conset meets Synset: A Preliminary Survey of an Ontological Lexical Resource based on Chinese Characters</Title>
  <Section position="7" start_page="388" end_page="389" type="evalu">
    <SectionTitle>
5 Applications and Future Development
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="388" end_page="389" type="sub_section">
      <SectionTitle>
5.1 Sense Prediction and Disambiguation
</SectionTitle>
      <Paragraph position="0"> Based on the initial version of the proposed resources, Hsieh (2005b) has proposed a semantic class prediction model which aims to gain the possible semantic classes of unknown two-characters words. The results obtained shows that, with this knowledge resource, the system can achieve fairly high level of performance. Meaning relevant NLP TaskssuchasWordSenseDisambiguationarealso in preparation.</Paragraph>
    </Section>
    <Section position="2" start_page="389" end_page="389" type="sub_section">
      <SectionTitle>
5.2 Interfacing Hantology, HanziNet and
Chinese Wordnet
</SectionTitle>
      <Paragraph position="0"> Interfacing ontologies and lexical resources has been a research topic in the coming age of semantic web. In the case of Chinese, three existing lexicalresources(uni610Funi7B26Radicals::Hantology(Chou and Huang (2005))- uni5B57 Characters::HanziNet uni8A5E Words::Chinese Wordnet) constitutes an integrated 3-level knowledge scenario which would provide important insights into the problems of understanding the complexities and its interaction with Chinese natural language.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>