<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1411">
  <Title>EXPERIMENTS USING STOCHASTIC SEARCH FOR TEXT PLANNING</Title>
  <Section position="7" start_page="105" end_page="106" type="concl">
    <SectionTitle>
7 Discussion
</SectionTitle>
    <Paragraph position="0"> It is necessary to be careful in evaluating:these results, which are 0nly as good as the evaluation function. This is certainly flawed in major ways. The texts are of a specific type, there are only three of them and we have not used all rhetorical relations. Some independent evaluation by human readers is imperative at this point. The texts are especially limited by the fact that there is no account taken Of the possibilities for aggregation , *embedding etc. in the trees that are produced: NevertheleSs * the approach looks promising enough that it is a real candidate to be used with the ILEX syste m. Future work needs to look at improving the characterisation of good trees and if possible *introducing more natural crossover/mutation operations. Future work could also consider extending the scope of the algorithm to deal with aspects of content determination as well as* structuring.</Paragraph>
  </Section>
class="xml-element"></Paper>