<?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="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Language modeling is a description of natural language and a good language model can help to improve the performance of the natural language processing.</Paragraph>
    <Paragraph position="1"> Traditional statistical language model (SLM) is fundamental to many natural language applications like automatic speech recognitionP  P. Different statistical models have been proposed in the past, but n-gram models (in particular, bi-gram and tri-gram models) still dominate SLM research. After that, other approaches were put forward, such as the combination of statistical-based approach and  P. But when the models are applied, the crucial disadvantages are that they can't represent and process the semantic information of a natural language, so they can't adapt well to the environment with changeful topics.</Paragraph>
    <Paragraph position="2"> Ontology was recognized as a conceptual modeling tool, which can descript an information system in the semantic level and knowledge level. After it was first introduced in the field of</Paragraph>
  </Section>
class="xml-element"></Paper>