<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-0202">
  <Title>Kaplan, J., Cooperative Responses from a Portable</Title>
  <Section position="2" start_page="1" end_page="1" type="relat">
    <SectionTitle>
2 Related work
</SectionTitle>
    <Paragraph position="0"> Discourse annotation is probably one of the most challenging domains that involves almost all aspects of language, from morphology to pragmatics. It is of much importance in a number of areas, besides QA, such as MT or dialogue. A number of discourse annotation projects (e.g. PALinkA (Orasan, 2003), MULI (Baumann et ali., 2004), DiET (Netter et ali. 1998), MATE (Dybkjaer et ali., 2000)) mainly deal with reference annotations (be they pronominal, temporal or spatial), which is clearly a major problem in discourse. Discourse connectives and their related anaphoric links and discourse units are analyzed in-depth in PDTB (Miltasakaki et ali.</Paragraph>
    <Paragraph position="1"> 2004), a system now widely used in a number of NL applications. RST discourse structures are also identified in the Treebank corpora.</Paragraph>
    <Paragraph position="2"> All these projects show the difficulty to annotate discourse, the subjectivity of the criteria for both the bracketing and the annotations. Annotation tasks are in general labor-intensive, but results in terms of discourse understanding are rewarding. Customisation to specific domains or forms of discourse and the definition of test-suites are still open problems, as outlined in PDTB and MATE.</Paragraph>
    <Paragraph position="3"> Our contribution is more on the pragmatic side of discourse, where there is little work done, probably because of the complexity of the notions involved and the difficulty to interpret them. Let us note (Strenston, 1994) that investigates complex pragmatic functions such as performatives and illocutionary force. Our contribution is obviously inspired by abstract and generic categorizations in pragmatics, but it is more concrete in the sense that it aims at identifying precise cooperative functions used in everyday life in large-public applications. In a first stage, we restrict ourselves to written QA pairs such as FAQ, Forums and email messages, which are quite well representative of short cooperative discourses (see 3.1).</Paragraph>
  </Section>
class="xml-element"></Paper>