<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1619">
  <Title>Extremely Lexicalized Models for Accurate and Fast HPSG Parsing</Title>
  <Section position="8" start_page="161" end_page="161" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> We developed an extremely lexicalized probabilistic model for fast and accurate HPSG parsing.</Paragraph>
    <Paragraph position="1"> The model is very simple. The probabilities of parse trees are defined with only the probabilities of selecting lexical entries, which are trained by the discriminative methods in the log-linear model with features of word trigrams and POS 5-grams as defined in the CCG supertagging. Experiments revealed that the model achieved impressive accuracy as high as that of the previous model for the probabilistic HPSG and that the implemented parser runs around four times faster.</Paragraph>
    <Paragraph position="2"> This indicates that accurate and fast parsing is possible using rather simple mechanisms. In addition, we provided another probabilistic model, in which the probabilities for the leaf nodes in a parse tree are given by the probabilities of supertagging, and the probabilities for the intermediate nodes are given by the previous phrase-structure-based model. The experiments demonstrated not only speeds significantly increased by three to four times but also impressive improvement in parsing accuracy by around two points in precision and recall. null We hope that this research provides a novel approach to deterministic parsing in which only lexical selection and little phrasal information without packed representations dominates the parsing strategy.</Paragraph>
  </Section>
class="xml-element"></Paper>