<?xml version="1.0" standalone="yes"?>
<Paper uid="E06-2028">
  <Title>Bayesian Network, a model for NLP?</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> When a pronoun refers to a linguistic expression previously introduced in the text, it is anaphoric.</Paragraph>
    <Paragraph position="1"> In the sentence Nonexpression of the locus even when it is present suggests that these chromosomes[...], the pronoun it refers to the referent designated as 'the locus'. When it does not refer to any referent, as in the sentence Thus, it is not unexpected that this versatile cellular... the pronoun is semantically empty or non-anaphoric.</Paragraph>
    <Paragraph position="2"> Any anaphora resolution system starts by identifying the pronoun occurrences and distinguishing theanaphoric and non-anaphoric occurrences of it.</Paragraph>
    <Paragraph position="3"> The first systems that tackled this classification problem were based either on manually written rules or on the automatic learning of relevant surface clues. Whatever strategy is used, these systems see their performances limited by the quality of knowledge they exploit, which is usually only partially reliable and heterogeneous.</Paragraph>
    <Paragraph position="4"> This article describes a new approach to go beyond the limits of traditional systems. This approach stands on the formalism, still little exploited for NLP, of Bayesian Network (BN). As a probabilistic formalism, it offers a great expression capacity to integrate heterogeneous knowledge in a single representation (Peshkin, 2003) as well as an elegant mechanism to take into account an a priori estimation of their reliability in the classification decision (Roth, 2002). In order to validate our approach wecarried out various experiments on a corpus made up of abtsracts of genomic articles.</Paragraph>
    <Paragraph position="5"> Section 2 presents the state of the art for the automatic recognition of the non-anaphoric occurences of it. Our BN-based approach is exposed in section 3. The experiments are reported in section 4, and results are discussed in section 5.</Paragraph>
  </Section>
class="xml-element"></Paper>