<?xml version="1.0" standalone="yes"?>
<Paper uid="E06-2028">
  <Title>Bayesian Network, a model for NLP?</Title>
  <Section position="5" start_page="197" end_page="197" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> Our system can of course be enhanced along the previous axes. However, it is interesting to note 9We have completed the Clement's SVM score for the same biological corpus to compare its results with ours. 10Like in the sentence It is assumed that the SecY protein of B. subtilis has multiple roles...</Paragraph>
    <Paragraph position="1"> 11Like in the sentence It is assumed to play a role in ... 12For example Thus, it appears T3SO4 has no intrinsic...</Paragraph>
    <Paragraph position="2"> that it achieves better results than the comparable state-of-the art systems, although it relies on the same set of rules and surface clues. This comparison confirms the fact that the BN model proposes an interesting way to combine the various clues, some of then being only partially reliable.</Paragraph>
    <Paragraph position="3"> We are continuing our work and expect to confirm the contribution of BN to NLP problems on a task which is more complex than the classification of it occurences: the resolution of anaphora.</Paragraph>
  </Section>
class="xml-element"></Paper>