<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1429">
  <Title>Knowledge Acquisition for Natural Language.Generation</Title>
  <Section position="8" start_page="221" end_page="222" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> The expert system community believes that it is worth interacting with experts using structured KA techniques, instead of just informally chatting to them or non-interactively studying what they do (as  happens in a traditional corpus analysis). We believe 'structured KA techniques ran also:he, useful in developing NLG systems, but they are not a panacea and need to be used with some caution.</Paragraph>
    <Paragraph position="1"> In retrospect, KA was probably most effective in STOP when used as a source of hypotheses about smoker categories, detailed content rules, the phrasing of messages, and so forth. But ideally these hypotheses should have been tested and refined using statistical data about smokers and small-scale evaluation exercises ..... :.- : ., Of course, a key problem in STOP was that we were trying to produce texts (personalised smoking-cessation leaflets) which were not currently produced by humans; and hence there were perhaps no real human experts on producing STOP texts. It would be interesting to see if structured KA techniques were more effective for developing systems which produced texts that humans do currently write, such as weather forecasts and instructional texts.</Paragraph>
  </Section>
class="xml-element"></Paper>