<?xml version="1.0" standalone="yes"?>
<Paper uid="P02-1042">
  <Title>Building Deep Dependency Structures with a Wide-Coverage CCG Parser</Title>
  <Section position="8" start_page="379" end_page="379" type="concl">
    <SectionTitle>
7 Conclusions and Further Work
</SectionTitle>
    <Paragraph position="0"> This paper has shown that accurate, efficient wide-coverage parsing is possible with CCG. Along with Hockenmaier and Steedman (2002b), this is the first CCG parsing work that we are aware of in which almost 98% of unseen sentences from the CCGbank can be parsed.</Paragraph>
    <Paragraph position="1"> The parser is able to capture a number of long-range dependencies that are not dealt with by existing treebank parsers. Capturing such dependencies is necessary for any parser that aims to support wide-coverage semantic analysis--say to support question-answering in any domain in which the difference between questions like Which company did Marks sue? and Which company sued Marks? matters. An advantage of our approach is that the recovery of long-range dependencies is fully integrated with the grammar and parser, rather than being relegated to a post-processing phase.</Paragraph>
    <Paragraph position="2"> Because of the extreme naivety of the statistical model, these results represent no more than a first attempt at combining wide-coverage CCG parsing with recovery of deep dependencies. However, we believe that the results are promising.</Paragraph>
    <Paragraph position="3"> In future work we will present an evaluation which teases out the differences in extracted and in-situ arguments. For the purposes of the statistical modelling, we are also considering building alternative structures that include the long-range dependencies, but which can be modelled using better motivated probability models, such as generative models. This will be important for applying the parser to tasks such as language modelling, for which the possibility of incremental processing of CCG appears particularly attractive.</Paragraph>
  </Section>
class="xml-element"></Paper>