<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-1120">
  <Title>A New Chinese Natural Language Understanding Architecture Based on Multilayer Search Mechanism</Title>
  <Section position="6" start_page="7" end_page="7" type="concl">
    <SectionTitle>
5 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> A new Chinese NLU architecture based on Multilayer Search Mechanism (MSM) integrates almost all of NLU components into a uniform multilayer treelike platform and quantifles these components to use the search algorithm to flnd out the optimal result. Thus any component can be added into MSM conveniently. They only need to accept an input and give several outputs with scores. By experiments we can see that a practical system { CUP based on MSM improves the performance of Word-Seg to a certain extent. And its e-ciency is high enough for most practical applications.</Paragraph>
    <Paragraph position="1"> The cascade and the feedback mechanism are JUST the special cases of MSM. If greedy algorithm is used at each layer to expand the result with the lowest score, MSM becomes the cascade mechanism. If the weight of each layer except the feedback point is set 0, the MSM becomes the feedback mechanism.</Paragraph>
    <Paragraph position="2"> In the future we are going to add the Phrase Analysis, WSD (Word Sense Disambiguation) and Semantic Analysis components into CUP, because it is impossible to analyze some sentences correctly without semantic understanding and the Phrase Analysis helps to enhance the performance of Parsing. At last, CUP becomes a whole Chinese NLU platform with Word-Seg, POS Tagging, Phrase Analysis, Parsing, WSD and Semantic Analysis, six components from lower layers to higher layers.</Paragraph>
    <Paragraph position="3"> Under the framework of MSM, it becomes very easy to add these components.</Paragraph>
    <Paragraph position="4"> With the increasing of layers the handle speed must decrease. So some heuristic search algorithms will be used to improve the speed of searching while enhancing the speed of each component. Under the MSM framework, we can do these easily.</Paragraph>
    <Paragraph position="5"> The performance of each component should be improved in the future. At least, it is impossible for MSM to flnd out the correct analysis result if there is a component which cannot give a correct result within n-best results with a correct input. In addition, we are going to evaluate the performance of each component not just Word-Seg only.</Paragraph>
  </Section>
class="xml-element"></Paper>