A Personality-based Framework for Utterance Generation in Dialogue Applications.
François Mairesse, Marilyn A. Walker · 2008
Conversation is an essential component of social behaviour, one of the primary means by which humans express emo-tions, moods, attitudes and personality. Thus a key technical capability for dialogue applications, such as interactive nar-rative systems (INS), human robot interaction (HRI) and spo-ken dialogue systems (SDS), is the ability to support natural conversational interaction. However, system utterances in ex-isting systems are typically handcrafted, leading to problems of portability and scalability. We propose a framework for au-tomatically generating language projecting different person-ality traits based on the ‘Big Five ’ model of personality. We show that our PERSONAGE generator can produce utterances with recognisable personality for all Big Five traits, accord-ing to human judges. We also test the ability of PERSONAGE to vary the characters ’ personality in an existing interactive narrative system, showing that some forms of variation can be automatically obtained in a new domain, depending on the level of utterance representation.