How Do I Address You? Modelling addressing behavior based on an analysis of a multi-modal corpora of conversational discourse

摘要

Addressing is a special kind of referring and thus principles of multi-modal referring expression generation will also be basic for generation of address terms and addressing gestures for conversational agents. Addressing is a special kind of referring because of the different (second person instead of object) role that the referent has in the interaction. Based on an analysis of addressing behaviour in multi-party face-to-face conversations (meetings, TV discussions as well as theater plays), we present outlines of a model for generating multi-modal verbal and non-verbal addressing behaviour for agents in multi-party interactions.