Language is always generated and interpreted in a certain context, and the semantic, syntactic, and lexical properties of linguistic expressions reflect this. Interactive language understanding systems, such as language-based dialogue systems, therefore have to apply contextual information to interpret their inputs and to generate appropriate outputs, but are in practice very poor at this. This book contains a number of studies in Computational Pragmatics, the newly emerging field of study of how contextual information can be effectively brought to bear in language understanding and generation. The various chapters center around the conceptual, formal and computational modeling of context in general, of the relevant beliefs of dialogue participants in particular, and of the reasoning that may be applied to relate linguistic phenomena to aspects of the dialogue context. These issues are discussed both from a theoretical point of view and in relation to their roles in prototypical language understanding systems.