Building agile human/machine teams with controlled natural language

Abstract

The military and civilian cyber environment continues to grow in complexity with new capabilities and services appearing regularly. This richness of structure and variety needs to be understood and where possible mapped or modelled to enable situation awareness of the current status and potential threats as well as the constant changes to the environment. In our ongoing research for the International Technology Alliance, we have been investigating the potential value of Controlled Natural Languages (CNLs) to support agile human-machine systems to support shared situation awareness in a variety of domains and to enable intelligence reporting, fusion and dissemination. In this paper, we present this approach and provide a number of examples of use from a variety of domains, including profiles of insurgents, contacts, communities, and networks to support intelligence analysts and other operatives in the field. We have also applied this approach to the sensemaking process, and to a variety of activities to support intelligence analysts including hypotheses, exploration of rationale and assumption, presentation of complex information through storytelling, and interacting with information using a conversational interaction. We have also started human experiments with a conversational software agent to enable the field user to directly interact with such information in our CNL knowledgebase.