SimpleandEfficientModelFilteringinStatisticalMachine.PDFVIP

The Prague Bulletin of Mathematical Linguistics NUMBER 98 OCTOBER 2012 5–24 Simple and E?cient Model Filtering in Statistical Machine Translation Juan Pino, Aurelien Waite, William Byrne Department of Engineering, University of Cambridge, Cambridge, CB2 1PZ, U.K. Abstract Data availability and distributed computing techniques have allowed statistical machine translation (SMT) researchers to build larger models. However, decoders need to be able to retrieve information e?icie