You are here

DREAM: Detecting Relations, Entities, and Attributes Misinformation

Award Information
Agency: Department of Defense
Branch: Air Force
Contract: FA8750-14-C-0212
Agency Tracking Number: F131-051-1369
Amount: $743,604.00
Phase: Phase II
Program: SBIR
Solicitation Topic Code: AF131-051
Solicitation Number: 2013.2
Timeline
Solicitation Year: 2013
Award Year: 2014
Award Start Date (Proposal Award Date): 2014-09-16
Award End Date (Contract End Date): 2016-09-10
Small Business Information
12 Gill Street Suite 1400
Woburn, MA 01801
United States
DUNS: 000000000
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Georgiy Levchuk
 Scientist
 (781) 496-2467
 georgiy@aptima.com
Business Contact
 Thomas McKenna
Title: Chief Financial Officer
Phone: (781) 496-2443
Email: mckenna@aptima.com
Research Institution
 Stub
Abstract

ABSTRACT: Information fusion and knowledge conflict detection are required for many mission-critical intelligence analysis tasks. Using knowledge extracted from various sources, including entities, relations, and events, intelligence analysts identify relevant documents, integrate facts into summaries about current situation, and augment existing knowledge with inferred information. To deal with large amount of data, analysts require automated solutions to link events, entities and related knowledge across multiple sources. Aptima proposes to develop a system for Detecting Relation, Entity, and Attribute Misinformation (DREAM) to support processing of data with redundant, erroneous, and deceptive information. Our solution utilizes information extracted from text to find normal, conflicting and erroneous knowledge. When fully developed, DREAM will provide intelligence analysts with a powerful analysis tool that (1) automatically constructs knowledge graphs from raw text input; (2) finds conflicting knowledge fragments; (3) learns normally occurring knowledge; and (4) helps analysts understand the source of the conflicts in the data. BENEFIT: DREAM will allow intelligence analysts and commercial users to reduce the uncertainty in their knowledge bases and detect conflicting and anomalous patterns across multiple documents. For DoD applications, DREAM will support new PCPAD workflow by focusing the analysts on most critical data to reduce the analysis time and increase detection of hostile activities. For commercial applications, DREAM will enable faster and more accurate detection of deception in social media, online fraud, and social engineering activities.

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government