... forCube Pruning running in linear time in thebeam size. Empirically, we show a gain in running time of a standard machine translationsystem, at a small loss in accuracy.1 IntroductionSince its ... 2009), parsing (Huangand Chiang, 2005), sentence alignment (Riesa andMarcu, 2010), and in general in all systems combin-ing inexact beam decoding with dynamic program-ming under certain monotonic ... appearance in (Huang and Chiang,2005), the Cube Pruning (CP) algorithm has quicklygained popularity in statistical natural language pro-cessing. Informally, this algorithm applies to sce-narios in...