Researchers at IBM say they have created smart software that that translates text between English and 11 other languages including Chinese, Korean, Japanese, French, Italian, Russian, German, Spanish, Portuguese, Italian and Arabic.
Hosted as an internal IBM service since August 2008, n.Fluent offers a secure real time translation tool that translates text in web pages, electronic documents, Sametime instant message chats, and provides a BlackBerry mobile translation application.
According to IBM the software, n.Fluent was developed from an internal IBM crowdsourcing project where Big Blue’s nearly 400,000 employees in more than 170 countries, submit, update and continuously refine word translations. Every time it's used, n.Fluent "learns" and improves its translation engine. To date, the tool has been used by IBMers to translate more than 40 million words, IBM stated.
n.Fluent is just one of many IBM language projects. IBM says its volunteers also work on DigiCapE and Agora, two other language related crowdsourcing projects developed by IBM researchers. These technologies let people to easily locate, transcribe, synchronize, tag, caption and share audio from a video file. In 2007 IBM’s India Research Laboratory developed speech recognition software for Hindi, one of the key languages in India.
IBM said the software is used internally for now but could make it into a product or service in the future.
Gartner called automated speech translation one of the grand challenges IT faces in the coming years. Natural language processing will be a key feature of computers after researchers resolve challenges related to speech synthesis and recognition, and machine translation. Some "rudimentary" automated speech translation systems have been created, but "the complexity extends further when translation and output is required to a target language that is understandable to a human," Gartner says.
Language translation software is big business. For example, researchers at BBN have taken in over $30 million (£18m) from the US Defense Advanced Research Projects Agency over the past few years to fill out the agency’s Global Autonomous Language Exploitation (GALE) program. The goal of GALE is to translate and distill foreign language material (television shows and newspapers) in near real time, highlight salient information, and store the results in a searchable database, all with more than 90% accuracy by the end of the program. Through this process, GALE would help US analysts recognise critical information in foreign languages quickly so they could act on it in a timely fashion.