<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1429">
  <Title>Knowledge Acquisition for Natural Language.Generation</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> An important aspect of building natural-language generation (NLG) systems is knowledge acquisition.</Paragraph>
    <Paragraph position="1"> This is the process of acquiring the specific knowledge needed in a particular application about the domain, the language used in the domain genre, the readers of the texts, and so forth. Such knowledge influences, for example, the system's content selection rules (whether represented as schemas, production rules, or plan operators); the system's microplanning choice rules (lexicalisation, referring expression generation, aggregation); and perhaps even the system's grammar (if a genre grammar is needed, as is tile case, for example, with weather reports).</Paragraph>
    <Paragraph position="2"> To date, knowledge acquisition for NLG systems has largely been based on corpus analysis, informal interactions with experts, and informal feed-back from users (Reiter et al., 1997; Reiter and Dale, 2000). For example, the PlanDoc developers (McKeown et al., 1994) interviewed users to get a general understanding of the domain and user requirements; asked a single expert to write some example output texts; and then analysed this corpus in various ways. Other KA techniques used in the past for building NLG systems include letting domain experts specify content rules in pseudo-code (Goldberg et al., 1994) and ethnographic techniques such as observing doctors and patients in real consultations (Forsythe, 1995).</Paragraph>
    <Paragraph position="3"> As part of the .C/,ToP project (Reiter et al., 1999) to generate personalised smoking-cessation leaflets, we investigated using some of the structured KA techniques developed by the expert-system community (see, for example, (Scott et al., 1991)) for acquiring the knowledge needed by an NLG system. In this paper we summarise our experiences. Very briefly, our overall conclusion is that in STOP, structured KA was probably useful for getting insight into and formulating hypotheses about the knowledge needed by an NaG system. However, formulating detailed rules purely on the basis of such KA was not ideal, and it would have been preferable to use other information as well during this process, such as statistics about smokers and feedback from smoker evaluations of draft STOP leaflets.</Paragraph>
  </Section>
class="xml-element"></Paper>