<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2304">
  <Title>A Robust and Efficient Parser for Non-Canonical Inputs</Title>
  <Section position="6" start_page="23" end_page="23" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> The first results obtained during the evaluation campaign described in this paper are very interesting. They illustrate the relevance of using symbolic approaches for parsing non-canonical material. The technique described here makes it possible to use the same method and the same resources whatever the kind of input and offers the possibility to do chunking as well as deep analysis. Moreover, such techniques, provided that they are implemented with some control mechanisms, can be very efficient: our parser treat more than 4,000 words per second. It constitutes then an efficient tool capable of dealing with large amount of data. On top of this efficiency, the parser has good results in terms of bracketing, whatever the kind of material parsed.</Paragraph>
    <Paragraph position="1"> This second characteristics also shows that the system can be used in real life applications.</Paragraph>
    <Paragraph position="2"> In terms of theoretical results, such experimentation shows the interest of using constraints. First, they makes it possible to represent very finelevel information and offers a variety of control mechanisms, relying for example on the possibility of weighting them. Moreover, constraint relaxation techniques offer the possibility of building categories violating part of syntactic description of the grammar. They are then particularly well adapted to the treatment of non canonical texts. The formalism of Property Grammars being a fully constraint-based approach, it constitutes an efficient solution for the description of any kind of inputs.</Paragraph>
  </Section>
class="xml-element"></Paper>