Enabling visualization of events from unstructured text (HUMINT) on maps

Award Information
Agency:
Department of Defense
Branch:
Air Force
Amount:
$149,921.00
Award Year:
2012
Program:
SBIR
Phase:
Phase I
Contract:
FA8750-12-C-0063
Agency Tracking Number:
F112-036-1209
Solicitation Year:
2011
Solicitation Topic Code:
AF112-036
Solicitation Number:
2011.2
Small Business Information
Janya Inc.
1408 Sweet Home Road, Suite 1, Amherst, NY, -
Hubzone Owned:
N
Socially and Economically Disadvantaged:
N
Woman Owned:
Y
Duns:
360923960
Principal Investigator
 John Chen
 Sr. Reserach Scientist
 (716) 242-8417
 jchen@janya.com
Business Contact
 Rohini Srihari
Title: CEO
Phone: (716) 242-8404
Email: rohini@janya.com
Research Institution
 Stub
Abstract
ABSTRACT: Rapid visualization of events existing in unstructured data requires a system with the ability to accurately detect events and their arguments in such data. Currently, many systems that perform this task do so by relying on only sentential context. Those systems that do rely on document-wide context are more accurate but suffer in terms of efficiency in that they need to process the input document repeatedly, or that in order to process the current input document they require processing of related documents. We experiment with novel approaches for event extraction that rely on document-wide context. Here, event extraction includes event mention detection, event argument detection, and event coreference resolution. One approach is maximum entropy modeling with document-wide features. Another approach models the document as a Dynamic Bayesian Network. They offer the promise of event extraction with higher recall, precision, and speed than previous systems. BENEFIT: The main anticipated benefit of this work includes the development of a system that (i) extracts event mentions and event arguments from unstructured data with higher recall and precision, and (ii) performs event coreference resolution on these event mentions with higher accuracy than was previously attainable. Furthermore, the document-wide classification techniques developed on this project might be transferred to improve the accuracy of other information extraction modules.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government