12 May 2016 Collaborative human-machine analysis to disambiguate entities in unstructured text and structured datasets
Author Affiliations +
Abstract
Intelligence analysts demand rapid information fusion capabilities to develop and maintain accurate situational awareness and understanding of dynamic enemy threats in asymmetric military operations. The ability to extract relationships between people, groups, and locations from a variety of text datasets is critical to proactive decision making. The derived network of entities must be automatically created and presented to analysts to assist in decision making.

DECISIVE ANALYTICS Corporation (DAC) provides capabilities to automatically extract entities, relationships between entities, semantic concepts about entities, and network models of entities from text and multi-source datasets. DAC’s Natural Language Processing (NLP) Entity Analytics model entities as complex systems of attributes and interrelationships which are extracted from unstructured text via NLP algorithms. The extracted entities are automatically disambiguated via machine learning algorithms, and resolution recommendations are presented to the analyst for validation; the analyst’s expertise is leveraged in this hybrid human/computer collaborative model. Military capability is enhanced by these NLP Entity Analytics because analysts can now create/update an entity profile with intelligence automatically extracted from unstructured text, thereby fusing entity knowledge from structured and unstructured data sources. Operational and sustainment costs are reduced since analysts do not have to manually tag and resolve entities.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jack H. Davenport, "Collaborative human-machine analysis to disambiguate entities in unstructured text and structured datasets", Proc. SPIE 9851, Next-Generation Analyst IV, 985103 (12 May 2016); doi: 10.1117/12.2230880; https://doi.org/10.1117/12.2230880
PROCEEDINGS
7 PAGES


SHARE
Back to Top