FOR IMMEDIATE RELEASE

Solution provides breakthrough advances in translation software combining the strengths of both statistical and rule-based methodologies  

 McLean, VA (March 2, 2009) – AppTek, a leader in human language technology (HLT), today released the industry’s first complete hybrid machine translation (HMT) system, a full integration of statistical and rule-based methodologies to assist linguists, translators and analysts in achieving greater productivity and higher quality results in a timely and cost effective manner. AppTek’s hybrid approach to machine translation (MT) provides significant advances to automated translation of large volumes of speech and text data compiled from a variety of sources.  

“AppTek is the only human language technology provider to successfully develop a single system to enable fully-automatic, high quality machine translation,” said Mike Veronis, Head of Business Development at AppTek. “By providing the optimal features of both statistical and rule-based approaches, the amount of time that a user must spend editing and polishing the translated output can be reduced significantly.” 

AppTek’s HMT solution provides a full integration of both Machine Translation methodologies, rather than simply adding rules to the statistical system or a minor statistical module to the rule-based engine. Using the company’s statistical MT platform and augmenting it with its rich rule-based MT engine, AppTek’s HMT solution is pushing the state-of-the-art in Machine Translation design to the next level. The three key translation quality parameters of MT systems - fluency, informativeness, and adequacy – are now supported in one comprehensive system with greater performance, quality and accuracy. 

 “Since AppTek’s HMT platform is part of an integrated suite of HLT applications, the level of software and system support is considerably lower than the levels needed to support discrete MT platforms that use third-party software to build out applications,” said Steve Cook, Chief Technology Officer at AppTek. “Furthermore, business managers are able to provide more timely and high-quality intelligence and analysis to support the policy and strategic decision makers within their organization.” 

Machine Translation is the process of software translating a variety of textual media (document, speech output transcripts, text, PowerPoint presentations, Web pages, etc.) from one language to another. Prior to AppTek’s HMT, MT was typically implemented using one of two methodologies – statistical or rule-based. Statistical systems use examples and apply statistical techniques to a large body of language data to perform translations where rule-based systems use grammatical knowledge based on linguistic rules defined by the user. The advantages of statistical systems are that they have a higher level of fluency – the translated text reads better.  Rule-based systems do not always read as well, but have a higher level of informativeness – the translated information is often more accurate, but harder to read. Our hybrid MT combines the advantages of both approaches.  Organizations that utilize MT will find that HMT offers significant price and performance gains compared to deploying multiple platforms to achieve the same level of translation performance. 

ABOUT APPTEK

AppTek, headquartered in McLean, Virginia, is a developer of human language technology products with a complete suite for text and speech (voice) processing and recognition.  The Company also leads major research and development efforts to further the advancement in the field of developing better methods and technologies in the field of HLT.  AppTek's product offerings include machine translation (MT) and automatic speech recognition (ASR) for a growing list of more than 23 languages; multilingual information retrieval with query and topic search capabilities; name-finding applications; and integrated suites providing automatic speech recognition and machine translation in media monitoring of broadcast and telephony speech as well as handheld and wearable speech-to-speech translation devices.  The company has language professionals and computer scientists in offices around the world. For more information visit: www.apptek.com. 

CONTACT:

Chris Leach

This e-mail address is being protected from spambots. You need JavaScript enabled to view it

(703) 218-3555

 Click Here for PDF