From Context to Sentence Form

When generating utterances, humans may choose among a number of alternative sentence forms expressing the same propositional content. The context determines these decisions to a large extent. This paper presents a strategy to allow for such context-sensitive variation when generating text for a wearable, advice giving device. Several dimensions of context feed a model of the hearer's attention space, which, in terms of Information Structure Theory, determines the form of the sentence to be generated.