Introduction to special issue on machine learning for adaptivity in spoken dialogue systems

An introduction to a special issue on machine learning for adaptivity in spoken dialogue systems is presented. Researchers preparing the introduction to the special issue state that the research in the field of spoken dialogue systems has undergone significant changes over a certain period of time. This transformation has been due to the result of new momentum and fresh insights coming from the investigation of data-driven, statistical machine learning methods in three core areas of dialogue system research. These three core areas of dialogue system research are spoken language understanding, dialogue management, and natural language generation. These methods have the potential of introducing mathematically precise approaches to system design, optimization and evaluation, based on data collected from real user interactions with dialogue systems.