The Defense Advanced Research Projects Agency (DARPA) has awarded Raytheon BBN Technologies an additional $5.9 million in funding under the Multilingual Automatic Document Classification, Analysis and Translation (MADCAT) program. This award follows Raytheon BBN's success during the first four years of the MADCAT program. BBN is a wholly owned subsidiary of Raytheon.

The Raytheon BBN team's goal is to create a prototype system that provides accurate, relevant, distilled, actionable information to military commands and personnel.

If successful, the system will automatically convert foreign language text images, such as handwritten notes and machine-printed documents, into English transcripts without the use of linguists and analysts. When human analysis is necessary, linguists and analysts would be able to use the technology to more effectively and efficiently explore the content of documents of interest.

"Foreign language translation on the battlefield is slow, unreliable, difficult to access and expensive," said Prem Natarajan, head of Speech and Language Processing at Raytheon BBN Technologies.

"By putting translation capability directly in the hands of the end user, MADCAT technologies will help our troops understand handwritten and printed documents that could be of immediate importance to their safety and to the successful completion of their missions."

Under the contract, Raytheon BBN will:

+ Advance previous work under the MADCAT program to refine a laptop-deployable prototype translation system.

+ Integrate optical character recognition with Raytheon BBN's state-of-the-art translation and distillation techniques.

+ Develop novel methods to process handwritten text.