Parallel FDA5 for fast deployment of accurate statistical machine translation systems
Bicici, Ergun, Liu, Qun and Way, AndyORCID: 0000-0001-5736-5930
(2014)
Parallel FDA5 for fast deployment of accurate statistical machine translation systems.
In: ACL 2014, Ninth Workshop on Statistical MachineTranslation, 26-27 June, 2014, Baltimore, USA.
We use parallel FDA5, an efficiently parameterized and optimized parallel implementation of feature decay algorithms for fast deployment of accurate statistical
machine translation systems, taking only about half a day for each translation direction.
We build Parallel FDA5 Moses SMT systems for all language pairs in the WMT14 translation task and obtain SMT
performance close to the top Moses systems with an average of $3.49$ BLEU points difference using significantly less resources for training and development.