DARPA program language, text comprehension awards funding to Raytheon BBN TechnologiesNews
December 05, 2012
CAMBRIDGE, MA. Raytheon BBN Technologies won a $16 million in funding to develop exploration and filtering tools to improve text comprehension. The contract is under the Deep Exploration and Filter of Text (DEFT) program, which is sponsored by the Defense Advanced Research Projects Agency (DARPA) and the U.S. Air Force Research Laboratory.
While advances in language and speech technologies enabled government agencies to process and collect vast amounts of data, there are still technological roadblocks when it comes to discovering data that is implied but not explicitly stated within text. The DEFT program looks to improveve currently available analytical tools by designing a deep natural language exploration and filtering capability to uncover operationally significant information and then deliver relevant alerts to users.
"Much of the information that our analysts need is couched in ambiguous language,” says Prem Natarajan, Raytheon BBN Technologies executive vice president of Speech, Language & Multimedia. “The DEFT program aims to strip away that ambiguity and also to make it easier to integrate new facts into our existing knowledge bases in a meaningful way.”
Raytheon BBN scientists are tasked with meeting two goals of the DEFT program -- to develop new techniques to infer meaning, discover relationships, and detect anomalies in text; and to research and develop tools to integrate new, individual facts into existing large information stores. The improved understanding will enable analysts and others to exploit surface information in massive data archives as well as uncover interconnections between different data elements and strategic and tactical nuances.