In this paper, we discuss the problem of generating natural anaphora in assembly instructional texts. We rst present a detailed account of grammatical and lexical anaphora and we examine a set of constraints for selecting these devices. As language is often redundant and an optimal referring expression is computationally prohibitive, we take the view that the generation of anaphora should be based on a thorough linguistic study and should lead to a natural choice, rather than an optimal one. We then present a text generation system built to evaluate the linguistic constraints. This component takes as input a speci cation of the sequence of actions to be performed in a cooking recipe and selects and produces the most appropriate anaphoric device to be used in the text.
Leila Kosseim, Agnès Tutin, Richard I. Kitt