AppTek Scores Highest in 2009 NIST Testing of Machine Translation Systems

Results validate company`s hybrid machine translation approach of fully
integrating both statistical and rule-based methodologies
MCLEAN, Va.--(Business Wire)--
AppTek, a leader in human language technology (HLT), today announced it received
the highest overall scores among the commercial vendors who participated in the
National Institute of Standards and Technology`s (NIST) 2009 Open Machine
Translation Evaluation. The industry`s first complete hybrid machine translation
(HMT) system, AppTek`s patent-pending solution is 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.

For the third consecutive year, AppTek scored the highest in both "noisy data,"
the most challenging type of content, and "informativeness," the measurement of
the usefulness and accuracy of the translation for the user. AppTek`s HMT
solution provides a full integration of both MT 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 MT design to the next level. As seen through the
2009 NIST evaluation, the three key translation quality parameters of MT systems
- fluency, informativeness, and adequacy - are effectively supported by AppTek`s
comprehensive HMT system, providing greater performance, quality and accuracy
across the board.

"The NIST evaluation further validates our hybrid approach to machine
translation as being the most efficient and useful in providing accurate and
informative multi-lingual information retrieval," said Hassan Sawaf, Chief
Scientist at AppTek. "As a company that has spent years developing innovative MT
solutions, we look forward to our continued successful participation in the Open
NIST evaluations to ensure the industry remains focused on providing the best
machine translation solutions possible."

NIST published the results on their Web site at: http://www.nist.gov. NIST
conducts these evaluations in order to support MT research and help advance the
state of the art in MT technology, rather than as a competition. As such, the
results are not to be construed or represented as endorsements of any
participant's system or commercial product, or taken as official findings on the
part of NIST or the U.S. government.

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.

AppTek
Chris Leach
chris@w2comm.com
703-218-3555

Copyright Business Wire 2009