SYSTRAN’s Innovative Hybrid Machine Translation Technology to Assist in DARPA Project to Produce Language Translation Technologies
PARIS, FRANCE and SAN DIEGO, CA – December 9, 2009
SYSTRAN, the leading provider of language translation technologies, today announced it has been invited to join Raytheon BBN Technologies on the U.S. government’s GALE (Global Autonomous Language Exploitation) project.
U.S. forces operating around the globe must be able to understand a wide range of new and changing information, which often appears in foreign languages. The goal of GALE is to develop and apply software technologies to transcribe, translate and distill large volumes of speech and text in multiple languages. Such a capability will help U.S. analysts to find and interpret needed information quickly and effectively, regardless of language or medium. The research part of the program focuses on Chinese and Arabic.
BBN, a wholly-owned subsidiary of Raytheon Company (NYSE: RTN), is a legendary R&D organization responsible for innovations in a variety of fields, including speech and language processing, information security, networking, distributed systems, and sensing and control systems. The company has been awarded funding by the Defense Advanced Research Projects Agency (DARPA) as part of the GALE program.
“BBN is committed to achieving GALE’s goal of unprecedented accuracy and consistency by bringing together the best software technologies,” said John Makhoul, chief scientist at BBN. “Combining these innovative approaches will enable us to deliver solutions that automatically provide relevant, concise and actionable information to military command and personnel in a timely fashion. We believe that combining SYSTRAN’s Chinese-to-English machine translation (MT) hybrid approach with the BBN team’s statistical MT technologies will help boost performance towards our ambitious research objectives.”
SYSTRAN, which has been in the translation technology business since 1968, provides enterprise translation products that allow its customers to customize programs to fit their needs. SYSTRAN’s hybrid MT product combines the predictability and language consistency of rule-based machine translation with the fluency of statistical MT.
“The GALE project will have extraordinary implications for commanders, analysts and other decision makers,” said Denis Gachot, president of SYSTRAN. “Accurately and consistently converting large quantities of foreign language data into timely, actionable intelligence in English will dramatically improve operational planning, crisis response and force protection. SYSTRAN looks forward to participating in this valuable endeavor.”
GALE systems must be able to perform at high levels of accuracy and consistency. Because language is fluid, customization is vital to helping create systems that can automatically adapt to different languages, topics and semantic nuances. SYSTRAN’s exclusive customization methodology gives users a unique ability to manage language data and reuse translated content, as well as create domain specific terminology.
SYSTRAN (www.systransoft.com) is the market leading provider of language translation software products and solutions for the desktop, enterprise and Internet that facilitate communication in 52 language combinations and in 20 vertical domains. Use of SYSTRAN products and solutions enhances multilingual communication and increases user productivity and time-savings. SYSTRAN delivers real-time language solutions for search, content management, online customer support, intra or inter-company collaboration, and eCommerce. With the ability to facilitate communication in 52 language combinations and in 20 vertical domains, SYSTRAN’s software is the choice of leading global corporations, portals including Apple, Yahoo! and AltaVista, and public agencies such as the US Intelligence Community and the European Commission.
SYSTRAN has been pioneering advances in machine translation for over four decades. Its latest achievement, SYSTRAN Hybrid MT, combines the predictability and language consistency of rule-based machine translation with the fluency of statistical MT.
SYSTRAN is headquartered in Paris, France with a North American office located in San Diego, California, USA.
SYSTRAN (Code ISIN FR0004109197, Bloomberg: SYST NM, Reuters: SYTN.LN) is listed on EuroNext Paris, Compartiment C. For more information, visit www.systransoft.com.
John Moran / Bill Donlan