<?xml version="1.0" standalone="yes"?>
<Paper uid="P02-1043">
  <Title>Generative Models for Statistical Parsing with Combinatory Categorial Grammar</Title>
  <Section position="8" start_page="6" end_page="6" type="concl">
    <SectionTitle>
8 Conclusion and future work
</SectionTitle>
    <Paragraph position="0"> We have compared a number of generative probability models of CCG derivations, and shown that our best model recovers 89.9% of word-word dependencies on section 23 of CCGbank. On section 00, it recovers 89.7% of word-word dependencies. These figures are surprisingly close to the figure of 90.9% reported by Collins (1999) on section 00, given that, in order to allow a direct comparison, we have used the same interpolation technique and beam strategy as Collins (1999), which are very unlikely to be as well-tuned to our kind of grammar.</Paragraph>
    <Paragraph position="1"> As is to be expected, a statistical model of a CCG extracted from the Treebank is less robust than a model with an overly permissive grammar such as Collins (1999). This problem seems to stem mainly from the incomplete coverage of the lexicon. We have shown that smoothing can compensate for entirely unknown words. However, this approach does not help on sentences which require previously unseen entries for known words. We would expect a less naive approach such as applying morphological rules to the observed entries, together with better smoothing techniques, to yield better results.</Paragraph>
    <Paragraph position="2"> We have also shown that a statistical model of CCG benefits from word-word dependencies to a much greater extent than a less linguistically motivated model such as Collins' Model 1. This indicates to us that, although the task faced by a CCG parser might seem harder prima facie, there are advantages to using a more linguistically adequate grammar.</Paragraph>
  </Section>
class="xml-element"></Paper>