<?xml version="1.0" standalone="yes"?>
<Paper uid="W96-0110">
  <Title>Statistical Models for Deep-structure Disambiguation</Title>
  <Section position="7" start_page="122" end_page="123" type="concl">
    <SectionTitle>
6. Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper, a deep-structure disambiguation system, integrating a semantic interpreter, a parser and a part-of-speech tagger, is developed. In this system, deep-structure ambiguity is resolved with the proposed integrated score function. This integrated score function incorporates the various knowledge sources, including parts-of-speech, syntax and semantics, in a uniform formulation to resolve the ambiguities at the various levels. Based on the integrated score function, the lexical score function, the syntactic score function, the case score function and the sense score function are derived accordingly. In addition, different models are denved in this paper to carry out case identification and word-sense discrimination.</Paragraph>
    <Paragraph position="1"> To reduce the estimation error from maximum likelihood estimation, the Good-Tufing's  smoothing method is also applied. Parameter smoothing is shown to improve the performance significantly. Finally, the parameters are adapted by using the robust discriminative learning algorithm. With this learning algorithm, 17.4% error reduction rate for sense discrimination, 50.7% for case and 47.4% for parsing accuracy are obtained compared with the baseline system. These results clearly demonstrate the superiority of the proposed models for deep-structure disambiguation.</Paragraph>
  </Section>
class="xml-element"></Paper>