<?xml version="1.0" standalone="yes"?>
<Paper uid="E91-1021">
  <Title>USING PLAUSIBLE INFERENCE RULES IN DESCRIPTION PLANNING</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
CONCLUSION
</SectionTitle>
    <Paragraph position="0"> This paper has discussed how, by anticipating the user's inferences, better explanations may be generated and assumptions about the user's knowledge updated in a more principled way. Although there are problems with the approach - particularly the difficulty of reliably predicting the user's inferences - it seems to provide a more principled way of selecting certain utterance types than existing multi-sentence 'text generation systems. Other question - 123 answering systems have attempted to simulate the user's inferences in order to block false inferences (Joshi etal., 1984; Zuckerman, 1990), and particular inferences have been considered in lexical choice (Reiter, 1990) and in generating narrative summaries (Cook et al., 1984). However, it has not been used previously as a general technique for selecting between different options in an description. null Considering what is implicitly conveyed in different types of description may also begin to explain some of the empirically derived results used in other systems. For example, the GIBBER system generally chooses to begin a description with class identification or with a comparison, as most information may be inferred from these (compared with mentioning specific attributes). This may be One of the principles influencing the organisation of the discourse strategies developed by McKeown (1985).</Paragraph>
    <Paragraph position="1"> The general approach would also suggest that experts might prefer structural descriptions to process descriptions (Paris, 1988) because they can already infer the process description from the structural, the former therefore conveying more implicit information.</Paragraph>
    <Paragraph position="2"> By looking at possible plausible inferences when planning descriptions we attempt give a better solution to the problem of determining what to say given a particular communicative goal. The approach has potential for generating more memorable descriptions, where different types of statement are used to re-inforce some information, as well showing us how to economically convey a great deal of information, where some of this information may be implicit. It does not provide a solution to the problem of determining how to structure this communicative content (considered in much other research), though we may find that by: considering further how people incrementally learn from descriptions we may obtain better structured text.</Paragraph>
    <Paragraph position="3"> The prototype system has been fully implemented, but much further research is needed. The inference rules, user modelling and scoring functions need to be further developed, and other influences on text structure (such as focus and higher level rhetorical relations) incorporated into the overall model.</Paragraph>
  </Section>
class="xml-element"></Paper>