<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2016">
  <Title>Markov model</Title>
  <Section position="9" start_page="126" end_page="126" type="concl">
    <SectionTitle>
6 Discussion and Future Work
</SectionTitle>
    <Paragraph position="0"> Due to the hierarchical structure of a HHMM, the model has the advantage of being able to reuse information for repeated sub-models. Thus the HHMM can perform more accurately and requires less computational time than the HMM in certain situations.</Paragraph>
    <Paragraph position="1"> The merging and flattening techniques have been shown to be effective and could be applied to many kinds of data with hierarchical structures. The methods are especially appealing where the model involves complex structure or there is a shortage of training data. Furthermore, they address an important issue when dealing with small datasets: by using the hierarchical model to uncover less obvious structures, the model is able to increase model performance even over more limited source materials. The experimental results have shown the potential of the merging and partial flattening techniques in building hierarchical models and providing better handling of states with less observation counts. Further research in both experimental and theoretical aspects of this work is planned, specifically in the area of reconstructing hierarchies where recursive formations are present and formal analysis and testing of techniques. null</Paragraph>
  </Section>
class="xml-element"></Paper>