<?xml version="1.0" standalone="yes"?>
<Paper uid="C69-1301">
  <Title>A DIRECTED RANDOM PARAGRAPH GENERATOR</Title>
  <Section position="4" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6. CONCLUSION
</SectionTitle>
    <Paragraph position="0"> The paragraph generator is currently operational, and produces output in reasonable times. Using the strategies for achieving development and cohesion so far developed, it is capable of generating ten--sentence strings in approximately fifteen seconds. Some of the main difficulties connected with the omtput are the following: (i) Deficiencies in the co-occurremce data affect the quality of individual sentences. For example, some nouns have very few dependents, a characteristic deriving from their behavior in the text on which the data is based; the selection of one of these nouns in a sentence may nullify the effect of applying strategies for development or cohesion. In general a generated paragraph is only as strong as the weakest link; defective single sentences can disturb the implementation of structural principles.</Paragraph>
    <Paragraph position="1"> (2) The grammar permits the generation of simple sentences only. Complex or compound sentences can, of course, be created by the device of juxtaposing these simple sentences with the help of conjunctions or relatives; the conditions under which this can be done remain to be specified.</Paragraph>
    <Paragraph position="2"> (3) The creation of &amp;quot;lexical fields&amp;quot; (containing, e.g~ such words as &amp;quot;to photograph,&amp;quot; &amp;quot;camera,&amp;quot; &amp;quot;film,&amp;quot;) would greatly increase the effect of cohesiono Distributional data for the formation of such &amp;quot;fields&amp;quot; is not readily available; if the classes are to be intuitively created,  --36-the result will be inconsistent with our present system of classification.</Paragraph>
    <Paragraph position="3"> Study of these problems continues through analysis of the output. The effects of strengthening or relaxing various criteria for achieving development and cohesion have been observed in a series of experiments. The use of alternative sets of language input data (e.g., different dependent probabilities or semantic classes) is also contemplated. (It should be emphasized that the program is not oriented on a particular language or set of language data.) The experimental design of the generation program is consistent with this kind of modification.</Paragraph>
  </Section>
class="xml-element"></Paper>