<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2141">
  <Title>Local context templates for Chinese constituent boundary prediction</Title>
  <Section position="4" start_page="979" end_page="979" type="concl">
    <SectionTitle>
6. Conclusions
</SectionTitle>
    <Paragraph position="0"> The paper proposed a constituent boundary prediction algorithm based on local context templates. Its characteristics can be summarized as follows: * The simple definition of the local context templates made the training procedure very easy.</Paragraph>
    <Paragraph position="1"> * The three-stage training procedure guarantees that only the useful trigram templates can be learned. Thus, the data sparseness problem was partially overcome. * The high coverage of different types of projected templates assures a higher overall prediction accuracy.</Paragraph>
    <Paragraph position="2"> * The multiple output mode provides the possibility to describe different boundary ambiguities.</Paragraph>
    <Paragraph position="3"> * The algorithm runs very fast, surpasses the HMM-based algorithm in accuracy and efficiency.</Paragraph>
    <Paragraph position="4"> There are a few possible improvement which may raise performance flwther. Firstly, some lexical-based templates, such as prepositions as left restriction, may improve performance further - this needs to be investigated. The introduction of the automatic identifiers for some special structures, such as conjunction structures or collocation structures, may reduce the prediction errors due to the long distance dependency problem. Finally, more training data is ahnost certain to improve results.</Paragraph>
  </Section>
class="xml-element"></Paper>