<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1014">
  <Title>Parsing the WSJ using CCG and Log-Linear Models</Title>
  <Section position="9" start_page="0" end_page="0" type="concl">
    <SectionTitle>
9 Conclusion
</SectionTitle>
    <Paragraph position="0"> A major contribution of this paper has been the development of a parsing model for CCG which uses all derivations, including non-standard derivations.</Paragraph>
    <Paragraph position="1"> Non-standard derivations are an integral part of the CCG formalism, and it is an interesting question whether efficient estimation and parsing algorithms can be defined for models which use all derivations.</Paragraph>
    <Paragraph position="2"> We have answered this question, and in doing so developed a new parsing algorithm for CCG which maximises expected recall of dependencies.</Paragraph>
    <Paragraph position="3"> We would like to extend the dependency model, by including the local-rule dependencies which are used by the normal-form model, for example. However, one of the disadvantages of the dependency model is that the estimation process is already using a large proportion of our existing resources, and extending the feature set will further increase the execution time and memory requirement of the estimation algorithm.</Paragraph>
    <Paragraph position="4"> We have also shown that a normal-form model performs as well as the dependency model. There are a number of advantages to the normal-form model: it requires less space and time resources for estimation and it produces a faster parser. Our normal-form parser significantly outperforms the parser of Clark et al. (2002) and produces results at least as good as the current state-of-the-art for CCG parsing. The use of adaptive supertagging and the normal-form constraints result in a very efficient wide-coverage parser. Our system demonstrates that accurate and efficient wide-coverage CCG parsing is feasible.</Paragraph>
    <Paragraph position="5"> Future work will investigate extending the feature sets used by the log-linear models with the aim of further increasing parsing accuracy. Finally, the oracle results suggest that further experimentation with the supertagger will significantly improve parsing accuracy, efficiency and robustness.</Paragraph>
  </Section>
class="xml-element"></Paper>