<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1087">
  <Title>Acquiring the Meaning of Discourse Markers</Title>
  <Section position="10" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusions and future work
</SectionTitle>
    <Paragraph position="0"> We have proposed corpus-based techniques for classifying discourse markers along three dimensions: polarity, veridicality and type. For these tasks we were able to classify with accuracy rates of 90.7%, 91.8% and 93.5% respectively. These equate to error reduction rates of 71.5%, 69.1% and 84.5% from the baseline error rates. In addition, we determined which features were most informative for the different classification tasks.</Paragraph>
    <Paragraph position="1"> In future work we aim to extend our work in two directions. Firstly, we will consider finer-grained classification tasks, such as learning whether a causal discourse marker introduces a cause or a consequence, e.g. distinguishing because from so. Secondly, we would like to see how far our results can be extended to include adverbial discourse markers, such as instead or for example, by using just features of the clauses they occur in.</Paragraph>
  </Section>
class="xml-element"></Paper>