Expanded global access to diverse means of communication is resulting in more information being produced in more languages more quickly than ever before. The volume of information encountered by DoD, the speed at which it arrives, and the diversity of languages and media through which it is communicated make identifying and acting on relevant information a serious challenge. At the same time, there is a need to communicate with non-English-speaking local populations of foreign countries, but it is at present costly and difficult for DoD to do so.
{{all}}
Expanded global access to diverse means of communication is resulting in more information being produced in more languages more quickly than ever before. The volume of information encountered by DoD, the speed at which it arrives, and the diversity of languages and media through which it is communicated make identifying and acting on relevant information a serious challenge. At the same time, there is a need to communicate with non-English-speaking local populations of foreign countries, but it is at present costly and difficult for DoD to do so.
Natural language processing technologies have the potential to enable cross-cultural communication, but current technology is insufficient to the task of handling informal language. In October 2011, DARPA launched the Broad Operational Language Translation (BOLT) program to attempt to create new techniques for automated translation and linguistic analysis that can be applied to the informal genres of text and speech common in online and in-person communication.
BOLT is aimed at enabling communication with non-English-speaking populations and identifying important information in foreign-language sources by: 1) allowing English-speakers to understand foreign-language sources of all genres, including chat, messaging and informal conversation; 2) providing English-speakers the ability to quickly identify targeted information in foreign-language sources using natural-language queries; and 3) enabling multi-turn communication in text and speech with non-English speakers. If successful, BOLT will deliver all capabilities free from domain or genre limitations.
Phase I of five anticipated year-long phases of BOLT began in October 2011. The program’s initial focus areas include development of techniques for: automatically processing informal foreign-language speech and text; coping with varied pronunciation, incorrect and/or incomplete syntax, colloquialisms and idiomatic speech; and resolving references and correlating co-references.
Future phases of BOLT will include research into new techniques to enable computers to carry on multi-modal dialogues with humans, comprehend concepts, and generate responses in multilingual environments.