<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-1046">
  <Title>Parsing with generative models of predicate-argument structure</Title>
  <Section position="8" start_page="2" end_page="2" type="concl">
    <SectionTitle>
8 Conclusion and future work
</SectionTitle>
    <Paragraph position="0"> This paper has defined a new generative model for CCG derivations which captures the word-word dependencies in the corresponding predicate-argument structure, including bounded and unbounded long-range dependencies. In contrast to the conditional model of Clark et al. (2002), our model captures these dependencies in a sound and consistent manner. The experiments presented here demonstrate that the performance of a simple baseline model can be improved significantly if long-range dependencies are also captured. In particular, our results indicate that it is important not to restrict the model to local dependencies. Future work will address the question whether these models can be run with a less aggressive beam search strategy, or whether a different parsing algorithm is more suitable. The problems that arise due to the overly aggressive beam search strategy might be overcome if we used an n-best parser with a simpler probability model (eg. of the kind proposed by Hockenmaier and Steedman (2002b)) and used the new model as a re-ranker. The current implementation uses a very simple method of estimating the probabilities of multiple dependencies, and more sophisticated techniques should be investigated.</Paragraph>
    <Paragraph position="1"> We have argued that a model of the kind proposed in this paper is essential for parsing languages with freer word order, such as Dutch or Czech, where the model of Hockenmaier and Steedman (2002b) (and other models of surface dependencies) would systematically capture the wrong dependencies, even if only local dependencies are taken into account. For English, our experimental results demonstrate that our model benefits greatly from modelling not only local, but also long-range dependencies, which are beyond the scope of surface dependency models.</Paragraph>
  </Section>
class="xml-element"></Paper>