An Agent-Based Dialog System for Adaptive and Multimodal Interface: A Case Study

Graphical Interfaces using an agent-based dialog can handle errors and interruptions, and dynamically adapts to the current context and situation, the needs of the task performed, and the user model. This is especially true for the design of multimodal interfaces, where interaction designers need to physically explore and prototype new interaction modalities and therefore require development environments that especially support the interactivity and the dynamic of this creative development process. We argue that, in the domain of sophisticated human-machine interfaces, we can make use of the increasing tendency to design such interfaces as independent agents that themselves engage in an interactive dialogue (both graphical and linguistic) with their users. This paper focuses on the implementation of a flexible and robust dialogue system which integrates emotions and other influencing parameters in the dialogue flow. In order to achieve a higher degree of adaptability and multimodality, we present Spoken Language Dialogue System (SLDS) architecture. The manufacturing process of the oil plant (GLZ: Gas Liquefying Zone), is selected as an application domain in this study