Automatic Causality Determination and Narrative Extraction using the Semantic Inference and Filtering Tool (SIFT)

Award Information
Agency:
Department of Defense
Branch
Army
Amount:
$100,000.00
Award Year:
2011
Program:
STTR
Phase:
Phase I
Contract:
W911NF-11-C-0249
Agency Tracking Number:
A11A-010-0382
Solicitation Year:
2011
Solicitation Topic Code:
A11a-T010
Solicitation Number:
2011.A
Small Business Information
Intelligent Automation, Inc.
15400 Calhoun Drive, Suite 400, Rockville, MD, -
Hubzone Owned:
N
Socially and Economically Disadvantaged:
N
Woman Owned:
Y
Duns:
161911532
Principal Investigator:
Jyotirmaya Nanda
Senior Research Scientist
(301) 294-4634
jnanda@i-a-i.com
Business Contact:
Mark James
Director, Contracts and Proposals
(301) 294-5221
mjames@i-a-i.com
Research Institution:
Univ. of Illinois, Urbana-Champaign
Dan Roth
3322 Siebel Center
201 N. Goodwin Avenue
Urbana, IL, 61801-
(217) 244-7068
Nonprofit college or university
Abstract
Intelligent Automation Inc. (IAI) is teaming with subject matter expert Prof. Dan Roth from the University of Illinois at Urbana-Champaign (UIUC) to propose a web based tool to search, filter, and collaboratively work on"document chains"interactively. The proposed Semantic Inference and Filtering Tool (SIFT) will provide an intuitive interface coupled with advanced Natural Language Processing (NLP) tools for automatic causality determination and narrative extraction from online resources. The proposed web based front end will make it easier for users to interactively narrow down the search space and locate the key document chains they are interested in. The system will allow users to collect and create a personal workspace to work with the selected document chains. Document chain discovery will have a feedback mechanism by which search results can be interactively manipulated by modifying search and ranking parameters. There will be a social networking aspect to the system by which analysts can share and work together on shared workspaces containing one or more document chains. We also propose to develop a working prototype by the end of Phase I that will demonstrate many of these key capabilities to sequence online resources.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government