Human-Machine Conversations to Support Coalition Missions with QoI Trade-Offs

Abstract—Supporting coalition missions by means of net-worked information resources in a dynamic environment presents challenging problems, not least in terms of human-machine collaboration. Human users need to task the network to help them achieve mission objectives, while humans are also sources of mission-critical information. Information quality is highly variable, both due to the nature of the sources and the network capacity. We propose a natural language-based conversational approach to supporting human-machine working in a coalition mission context. We present a model for human-machine and machine-machine interactions in a realistic mission context, and evaluate the model using an existing surveillance mission scenario. The model supports the flow of conversations from full natural language to a form of Controlled English (CE) amenable to machine processing and automated reasoning, including high-level information fusion tasks and QoI trade-offs, and the enforcement of policies for security and resource management. We introduce a mechanism for presenting the gist of verbose CE expressions in a more convenient form for human users, and show how the conversational interactions supported by the model include requests for expansions and explanations. We discuss how these mechanisms can support QoI trade-offs and enforcement of security and management policies. I