Alan T. Clark

Learn More
To create intelligent collaborative systems able to anticipate and react appropriately to users' needs and actions, it is crucial to develop a detailed understanding of the process of collaborative reference. We developed a dyadic eye tracking methodology and metrics for studying the multimodal process of reference, and applied these techniques in an(More)
Multimodal reference resolution is an important component of intelligent user interfaces using natural language. We use multimodal context data – including dyadic gaze-to develop models to identify reference in natural conversation. Our approach uses a mixture of rule-based and automatically coded gaze-based, linguistic, spatial, and temporal features, and(More)
  • 1