June 10, 2008
MCLEAN, VA – June 10, 2008 – AppTek, a leader in human language technology (HLT), was the top performer in NIST’s Meteor evaluation and one of the top three performers in this year’s NIST MT evaluations. Both impartial evaluations cover the global machine translation to evaluate technologies from industry, government, and academia and measure their performance. As in NIST MT 06, AppTek scored very high with the participation of more than 30 MT organizations.
Using a truly hybrid machine translation system, combining a complete statistical and a complete rule-based system, AppTek participated in these evaluations and, again, proved the strength of its complete approach to translation both structured and unstructured (a.k.a. noisy) textual data. The Hybrid Machine Translation system tested, TranSphere HMT, uses its rich rule-based engine to augment & enhance its statistical MT platform and elevates the state-of-the-art in machine translation.
NIST has published the results on their website (www.nist.gov). NIST conducts these evaluations in order to support machine translation (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.