Raytheon BBN Technologies

The goal of the DARPA Global Autonomous Language Exploitation (GALE) program is to develop and apply computer software technologies to absorb, analyze, and interpret huge volumes of speech and text in multiple languages, eliminating the need for linguists and analysts and automatically providing relevant, distilled actionable information to military commands and personnel in a timely fashion. Automatic processing "engines" will convert and distill the data, delivering pertinent, consolidated information in easy-to-understand forms to military personnel and monolingual English-speaking analysts in response to direct or implicit requests.

Raytheon BBN's Integrated Approach

Raytheon BBN Technologies is leading a team that proposes to meet this goal through an approach that maximizes accuracy by integrating the transcription and translation processes with foreign speech and/or text as input and English text and distilled information as output, instead of using the traditional linked approach of speech-to-text (STT) followed by machine translation (MT) and distillation.

Because language, both speech and text, is fluid, automatic adaptation and contextually-aware processing will be used at all system levels to optimize performance by adapting to languages, dialects, topics, speakers, semantic nuance, and more. For the first time, MT and distillation technology will automatically adapt to the domain and terminology of interest to the user.

Raytheon BBN's GALE Team

• Raytheon BBN Technologies
• Cambridge University
• Georgia Institute of Technology
• Language Computer Corporation
• Language Weaver
• LIMSI
• MIT
• Northeastern University
• Sakhr Software
• University of Colorado
• University of Edinburgh
• University of Maryland
• University of Pennsylvania
• USC/Information Sciences Institute (ISI)