Integrating hard and soft information sources for D2D using controlled natural language

Abstract

We introduce an approach to integrating access to hard and soft information sources to provide better exploitation of all available sources in the context of coalition data-to-decision (D2D) chains. In terms of hard (sensor-based) sources we show how intelligence, surveillance, and reconnaissance (ISR) assets can be represented at a relatively high level in controlled natural language, and how this allows the automatic assignment of sensing assets to D2D tasks. We demonstrate how the use of Controlled English (CE) — a type of controlled natural language designed to be readable by a native English speaker whilst representing information in a structured, unambiguous form — supports the informed sharing of D2D tasks and assets between collaborating users in a coalition environment. Moreover, we show how CE can be used in the automatic extraction of information from unstructured and semi-structured text information sources, providing us with a uniform way to integrate these soft sources with the aforementioned hard sources.