Modelling politeness in natural language generation

One of the main objectives of research in Natural Language generation (NLG) is to account for linguistic variation in a systematic way. Research on linguistic politeness provides important clues as to the possible causes of linguistic variation and the ways in which it may be modelled formally. In this paper we present a simple language generation model for choosing the appropriate surface realisations of tutoring responses based on the politeness notion of face. We adapt the existing definition of face to the demands of the educational genre and we demonstrate how a politeness driven NLG system may result in a more natural and a more varied form of linguistic output.