Accession Number:

ADA564588

Title:

Integrating Hard and Soft Information Sources for D2D Using Controlled Natural Language

Descriptive Note:

Conference paper

Corporate Author:

IBM THOMAS J WATSON RESEARCH CENTER HAWTHORNE NY

Personal Author(s):

• Preece, Alun
• Pizzocaro, Diego
• Braines, Dave
• Mott, David
• Mel, Geeth de
• Pham, Tien

Report Date:

2012-09-20

Pagination or Media Count:

9.0

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.

Descriptors:

• *ENGLISH LANGUAGE
• *INFORMATION SYSTEMS
• *NATURAL LANGUAGE
• ACCESS
• INTELLIGENCE
• POLITICAL ALLIANCES
• RECONNAISSANCE
• SPEECH
• SURVEILLANCE

Subject Categories:

• Linguistics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE