<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2310">
  <Title>Anaphora Resolution in Multi-Person Dialogues</Title>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
6. Semantic Parallelism (Lappin and Leass, 1994):
</SectionTitle>
    <Paragraph position="0"> This heuristic gives preference to those noun phrases which have the same semantic role as the anaphor in question. This is a useful heuristic and can be implemented by a system that can identify semantic roles.</Paragraph>
    <Paragraph position="1"> 7. Pragmatic Heuristics: We use certain pragmatic heuristics that we have identified to be very specific to dialogue settings. These are of the following kinds * If one speaker asks a question, then the next speaker is likely to be the antecedent of the you that may occur in the former's sentence.</Paragraph>
    <Paragraph position="2"> * If a speaker makes an exclamation then he is likely to be the antecedent of the you in the speech of the speaker just before him.</Paragraph>
    <Paragraph position="3"> 8. Naive Character Building: This refers to a naive character model that we have used to implement a restricted knowledge-based representation of the dialogue, woven around all the noun entities that are present in the dialogue. To this end, we use a certain amount of world knowledge that is present apriori with the system, in the form of ontology and functionality of possible noun entities. For instance, we associate actions with each character based on their subject object relationship with the verbs that occur in the dialogues. Now for an anaphor we see if a possible antecedent has functionality of the action associated with the anaphor, implied by the verb of the sentence. if it is so, we then give higher credibility to this particular antecedent.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
2.5 Learning approach
</SectionTitle>
      <Paragraph position="0"> In most systems ((Mitkov, 1998),(Lappin and Leass, 1994)) the weights that are assigned for different anaphor-antecedent relationships are programmer dependent. Fixing these values in a adhoc fashion can clearly give rise to unstable behaviour. In our work, we use manually tagged corpora to evaluate the effectiveness of a given weight assignment; these can then be tuned using Genetic Algorithms(Goldberg, 1989). We use 2point crossover and mutation which are used in Standard Genetic Algorithm for Real Variables(Deb and Kumar, 1995).</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>