<?xml version="1.0" standalone="yes"?>
<Paper uid="I05-2003">
  <Title>A Hybrid Chinese Language Model based on a Combination of Ontology with Statistical Method</Title>
  <Section position="6" start_page="17" end_page="17" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we presented a hybrid Chinese language model based on a combination of ontology with statistical method. We discuss the modeling and evaluate its performance. In the test about texts reordering, our experiences show that our method can increase the performance of Chinese information retrieval about 17.1% and 13.5% at top 10 and top 100 documents measure level. In another test about texts similarity computing, F1-measure is above 95%.</Paragraph>
    <Paragraph position="1"> On the other hand, in the current disposal of our information processing, we only make use of some characteristics ontology and use some co-occurrence information, such as semantics, POS, context, position, distance, and etc. For the further research and experiment, we will be on the following: (1) Research on the characteristics of relations between semantics and combine with some mature natural language processing techniques. (2) Research traditional ontology representation to keep up with international stand. (3) Apply our key techniques to English information retrieval and cross-lingual information retrieval systems and study a general approach.</Paragraph>
  </Section>
class="xml-element"></Paper>