Using Plausible Inference Rules In Description Planning

Current approaches to generating multi-sentence text fail to consider what the user may infer from the different statements in a description. This paper presents a system which contains an explicit model of the inferences that people may make from different statement types, and uses this model, together with assumptions about the user's prior knowledge, to pick the most appropriate sequence of utterances for achieving a given communicative goal. I N T R O D U C T I O N Examples, analogies and class identification are used in many explanations and descriptions. Yet current text generation techniques all fail to tackle the problem of when an example, analogy or class is appropriate, what example, analogy or class is best, and exactly what the user may infer from a given example, analogy or class. McKeown, for example, in her identification schema (given in figure 1) includes the 'rhetorical predicates' identification (as an instance of some class), analogy, particular.illustration and attributive (McKeown, 1985). From each of these, different information could be inferred by the user. In a human explanation they might be used to efficiently convey a great deal of information about the object, or to reinforce some information about an object so it may be better recalled. Yet in McKeown's schema based approach the only mechanism for selecting between these different explanation options is the *This work was carried out while the author was at t h e depar tment of Artificial Intelligence, University of Edinburgh, funded by a post doctoral fellowship from the Science and Engineering Research Council. Thanks to Ehud Reiter, Paul Brna and to the anonymous reviewers for helpful comments . Identification (class &: attribute/function) (Analogy/Constituence/At tributive/Renaming/ Amplification}* Particular-Illustration/Evidence+ { Amplification/Analogy/At tributive) {Particular-Illustration/Evidence) Note: ' () ' indicates optionality, ' / ' alternatives, '+' that item may appear 1-n times, '*' 0-n times. Figure 1: McKeown's identification schema [McKeown 851 initial pool of knowledge available to be conveyed, and focus rules, which just enforce some local coherence on the discourse. A particular example or analogy could perhaps be selected using the functions interfacing the rhetorical predicates to the domain knowledge base, but this is not discussed in the theory. More recently, Moore has included examples, analogies etc. in her text planner (Moore, 1990). She includes planning operators to deseribeby-superclass, describe-by-abstraction, describe-byezample, describe-by-analogy and describe-by.partsand.use. Two of these are illustrated in figure 2. But again there are no principled ways of selecting which strategy to use (beyond, for example, possibly selecting an analogy if the analogous concept is known), and the effect of each strategy is th~ same that the relevant concept is 'known'. In reality, of course, the detailed effects of the different strategies on the hearer'e knowledge will be very different, and will depend on their prior knowl-