<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-2096">
  <Title>GENERATING COHERENT ARGUMENTATIVE PARAGRAPHS</Title>
  <Section position="8" start_page="0" end_page="0" type="concl">
    <SectionTitle>
CONCLUSION
</SectionTitle>
    <Paragraph position="0"> We have described a model for planning argumentafive paragraphs which can perform content selection and which allows the surface realization component to adapt lexical choice within each clause to the rhetorical function of file clause. The model relies on the fact that the same argumentative relations which can he used as specific rhetorical relations also participate in the lexicld description of verbs, adjectives, adverbs and determiners. null Oar model &amp;quot;also distinguishes between two types of argumentative relations: evaluative functions and topoi.</Paragraph>
    <Paragraph position="1"> Evaluatiun function retch information from the knowledge base and make it scalar and contextdependent, while topoi are purely rhetorical relations that link scMar propositions together according to the argumentative goal of the speaker. This two-stage content retrieval mechanism is in coatrast to most existing planners which assemble facts directly retrieved from the knowledge base, and do not mmsfonn them according to the pragmatic context (goals of the speaker a*al user model). The mec &amp;quot;lmnism is implemented using the FUF text generation system.</Paragraph>
    <Paragraph position="2"> Some of the open questions we face are: * Deciding whether to use a connective or not.</Paragraph>
    <Paragraph position="3"> * Deciding whether propositions can be left implicit and still be recoverable.</Paragraph>
    <Paragraph position="4"> . Combining several independent argumentative chains and deciding how to order the arguments in the combined structure.</Paragraph>
    <Paragraph position="5"> - Acquiring the argumentative lexical descrip-Acr~ DE COLING-92. NANTES, 23-28 AOtT 1992 6 4 3 l'koc. OF COL1NG-92, NANrI~s, AUG. 23-28, 1992 tions we need on a large scale * Scaling up the text planning mechanism to generate several paragraphs.</Paragraph>
    <Paragraph position="6"> In particular, when several independent argumentative chains support the same conclusion, argumentative relations alone cannot determine in which order they must be organized. We are currently investigating whether argumentative strategies similar to RST schemas can be combined with our technique. We are also evaluating bow other discourse aspects like topic progression can help in the planning of the paragraph.</Paragraph>
    <Paragraph position="7"> Acknowledgments. This work was supported by DARPA under contract N00039-84-C-0165, by NSF Grant IRT-84-51438 and by ONR Grant N00014-89-J-1782. I want to thank Kathy McKeown, Jacques Robin and Frank Z. Smadja for helping me write this paper and Chaya Ochs for helping with the corpus analysis and the implementation of evaluation functions.</Paragraph>
  </Section>
class="xml-element"></Paper>