Sushil Jajodia, Director, Center for Secure Information Systems, and Kun Sun, Associate Professor, Information Sciences and Technology, are collaborating with researchers at Dartmouth College to develop a suite of algorithms to automatically extract knowledge bases from technical documents. This work is motivated by the growing need for the U.S. government and for U.S. companies to understand the content of the documents within their own enterprises so that they can better protect the military secrets, intellectual property, personal information, financial information, and business plans contained therein. This requires an end-to-end solution across many different fields, such as natural language processing, computer vision, logic, and optimization, because technical documents are multimodal. To support these large-scale computational methods, the system the researchers are developing will require a huge number of computing resources in terms of central processing units, memory, and graphics processing units.
To date, the researchers have used existing resources at the two schools, but they are now proposing to develop a laboratory with locations at both schools for large-scale document generation consistent with a knowledge base. This proposed effort addresses only the equipment cost of machines and racks that will constitute the distributed computing system. The laboratory will enable them to design and test various methods to achieve this goal.
The researchers will receive $529,194 from the U.S. Department of the Navy for this work. Funding will begin in June 2020 and will conclude in late May 2021.