<?xml version="1.0" standalone="yes"?>
<Paper uid="E85-1027">
  <Title>A Computational Theory of Prose Style for Natural Language Generation</Title>
  <Section position="6" start_page="192" end_page="192" type="concl">
    <SectionTitle>
6. Status and Future Work: Computational
</SectionTitle>
    <Paragraph position="0"> Models of Text planning At the time this is being written, the core data structures and interpreters of the program have been implemented and debugged, along with the set of attachment-points and stylistic rule,, which ate necessary to reproduce the paragraphs. The ~ylistic planner is completely integrated with the language generation program and has produced texts for scene descriptions (McDonald and Conklin (forthcoming)), narrative summaries (Cook, Lehnert, McDonald, \[1984D, and two of the three paragraphs shown in Figure 1.</Paragraph>
    <Paragraph position="1"> Currently we are shifting domains to generate newspaper articles, in the style of the New York Tunes. We have only a single style worked out in detail, but we would like to handle styles involving alternative lexical choices, as well.</Paragraph>
    <Paragraph position="2"> Ultimately what is most exciting to us is the opportunity that we now have to use this framework to develop precise hypotheses about the nature of the &amp;quot;planning unit&amp;quot; in human language generatinn. This has been an important question in psycholinguistic research as well (Garrett \[19S2D. This continum our ongoing line of research on the psychological consequences of our computational analysis of generation. The following are a few of the questions that mutt be addressed in the _r~e__arch on planning: o What is the size of the planning units at various stages; .</Paragraph>
    <Paragraph position="3"> o What is the vocabula.w that the units are stated in, e.g. are conceptual and linguistic objects mixed together or are there distinct unit-types at different levels, with some means of cascading between levels; o Should units be modelled as &amp;quot;streams&amp;quot; with conceptual components passing in at one end and text passing out at the other, or are they &amp;quot;quanta&amp;quot; that must be processed in their entirety one after the other; and finally o Can the comnonents of a planning Unit be revised after they are selected, or may they only be refined. This appears to relate to similar questions in psycholinguistic research (see Oarrett \[1982\] for review).</Paragraph>
  </Section>
class="xml-element"></Paper>