<?xml version="1.0" standalone="yes"?>
<Paper uid="E06-1010">
  <Title>Constraints on Non-Projective Dependency Parsing</Title>
  <Section position="8" start_page="77" end_page="79" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have investigated a series of graph-theoretic constraints on dependency structures, aiming to find a better approximation than PROJECTIVITY for the structures found in naturally occurring data, while maintaining good parsing efficiency.</Paragraph>
    <Paragraph position="1"> In particular, we have defined the degree of non-projectivity in terms of the maximum number of connected components that occur under a dependency arc without being dominated by the head of that arc. Empirical experiments based on data from two treebanks, from different languages and with different annotation schemes, have shown that limiting the degree d of non-projectivity to 1 or 2 gives an average case running time that is linear in practice and allows us to capture about 98% of the dependency graphs actually found in the treebanks with d [?] 1, and about 99.5% with d [?] 2. This is a substantial improvement over the projective approximation, which only allows 75-85% of the dependency graphs to be captured exactly. This suggests that the integration of such constraints into non-projective parsing algorithms will improve both accuracy and efficiency, but we have to leave the corroboration of this hypothesis as a topic for future research.</Paragraph>
  </Section>
class="xml-element"></Paper>