<?xml version="1.0" standalone="yes"?>
<Paper uid="A97-1011">
  <Title>A non-projective dependency parser</Title>
  <Section position="14" start_page="69" end_page="70" type="concl">
    <SectionTitle>
8 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we have presented some main features of our new framework for dependency syntax. The most important result is that the new framework allows us to describe non-projective dependency grammars and apply them efficiently. This is a property  that will be crucial when we will apply this framework to a language having free word-order.</Paragraph>
    <Paragraph position="1"> Basically, the parsing framework combines the Constraint Grammar framework (removing ambiguous readings) with a mechanism that adds dependencies between readings or tags. This means that while the parser disambiguates it also builds up a dependency forest that, in turn, is reduced by other disambiguation rules and a global pruning mechanism. null This setup makes it possible to operate on several layers of information, and use and combine structural information more efficiently than in the original Constraint Grammar framework, without any further disadvantage in dealing with ambiguity.</Paragraph>
    <Paragraph position="2"> First preliminary evaluations are presented. Compared to the ENGCG syntactic analyser, the output not only contains more information but it is also more accurate and explicit. The ambiguity rate is reduced to a quarter without any compromise in correctness. We did not have access to other systems, and care must be taken when interpreting the results which are not strictly comparable. However, the comparison to other current systems suggests that our dependency parser is very promising both theoretically and practically.</Paragraph>
  </Section>
class="xml-element"></Paper>