<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-2019">
  <Title>A corpus-based approach to topic in Danish dialog[?]</Title>
  <Section position="10" start_page="113" end_page="113" type="concl">
    <SectionTitle>
5 Summary and future work
</SectionTitle>
    <Paragraph position="0"> We have shown that it is possible to generate algorithms for Danish dialog that are able to predict the topic expressions of utterances with near-human performance (success rates of 84-89%, F1 scores of 0.63-0.72).</Paragraph>
    <Paragraph position="1"> Furthermore, our investigation has shown that the most characteristic features of topic expressions are preverbal position (+pre), definiteness (+def), pronominal realisation (+pro), and non-subordination (-sub). This supports the traditional view of topic as the constituent in preverbal position. Most interesting is subordination in connection with certain matrix clauses. We discovered that NPs in epistemic matrix clauses were seldom topics. In complex constructions like these the topic expression occurs in the subordinate clause, not the matrix clause as would be expected. We suspect that this can be extended to the more general category of inter-personal matrix clauses.</Paragraph>
    <Paragraph position="2"> Future work on dialog coherence in Danish, particularly pronoun resolution, may benefit from our results. The centering model, originally formulated by Grosz et al. (1995), models discourse coherence in terms of a 'local center of attention', viz. the backward-looking center, Cb. Insofar as the Cb corresponds to a notion like topic, the corpus-based investigation reported here might serve as the empirical basis for an adaptation for Danish dialog of the centering model. Attempts have already been made to adapt centering to dialog (Byron and Stent, 1998), and, importantly, work has also been done on adapting the centering model to other, freer word order languages such as German (Strube and Hahn, 1999).</Paragraph>
  </Section>
class="xml-element"></Paper>