Providing personalized Internet services by means of context-aware spoken dialogue systems

Abstract

The widespread use of new mobile technology implementing wireless communications enables a new type of advanced applications to access information services on the Internet. In order to provide services which meet the user needs through intelligent information retrieval, the system must sense and interpret the user environment and the communication context. Though context-awareness is vital to provide services adapted to the user preferences, it cannot be useful if such services are difficult to access. The development of spoken dialogue systems for these applications facilitates interaction in natural language with the environment which is also benefited from contextual information. In this paper, we propose a framework to develop context-aware dialogue systems that dynamically incorporate user specific requirements and preferences as well as characteristics about the interaction environment, in order to improve and personalize web information and services. We have identified the major components for context-aware dialogue systems and placed them within a general-purpose architecture. The framework also describes a representation mode based on a dialogue register in order to share information between the elements of the architecture, and incorporates statistical methodologies for dialogue management in order to reduce the effort required for both the implementation of a new system and the adaptation to a new task. We have evaluated our proposal developing a travel-planning system, and provide a detailed discussion of its positive influence in the quality of the interaction and the information and services provided.