The Deep Exploration and Filtering of Text (DEFT) program was created to “assist warfighter with planning and decision-making by inferring implicit information in text, filtering redundancy and connecting like documents.”
The Defense Advanced Research Projects Agency (DARPA) will next this month
detail the union of advanced technologies from artificial intelligence,
computational linguistics, machine learning, natural-language fields it hopes to
bring together to build an automated system that will let analysts and others
better grasp meanings from large volumes of text documentation.
It all boils down to this, military operations officers have a difficult time searching through copious amounts of data in a short period of time. DARPA aims to combat that challenge with an automated and deep natural-language analysis that will process information almost effortlessly.
With personnel incapable of combing through just about 90% of the information that is dealt to them because of time constraints, invaluable data falls through the cracks. With the invention of the DEFT program, this sophisticated piece of intelligence will scan through material in order to discover the actionable information contained within them.
DEFT will also focus on changing the current landscape of linear processing, which is limited by the quantities of data in the stratosphere. DEFT will construct a more coordinated exploration of the available data. The program manager, Bonnie Dorr, put it best,
“Deft is attempting to create technology to make reliable inferences based on basic text. We want the ability to mitigate ambiguity in text by stripping away filters that can cloud meaning and by rejecting false information. To be successful, the technology needs to look beyond what is explicitly expressed in text to infer what is actually meant.”