A natural language interface for an intelligent universal situational awareness (USA) system

Abstract

Detecting and countering potential terrorist threats requires a synergistic conjunction of intelligent technologies. The paper describes an intelligent universal situation awareness (USA) system and in particular discusses a natural language front-end interface that is designed to reduce the impedance mismatch between the human and the machine. The effective translation of natural language semantics is critically dependent on an accelerated capability for learning. Hence, a conversational natural language is mapped onto a set of procedures, which effect directed mining and linking operations on a relational database. These procedures are written in a very high-level extensible language (VHLL), which serves to facilitate knowledge expression and maintenance operations. The VHLL is underpinned by expert compiler technology. Objects for directed mining and linking are invoked as rule consequents in a blackboard architecture. Using information hiding, objects can be visually displayed in the form of a tree to facilitate acquisition and maintenance operations. Finally, projected and restricted database views can be analyzed by a distinct high-level knowledge base to generate natural language reports. Most importantly, these reports provide the analyst with immediate feedback, which serves to catalyze the generation of subsequent queries.