Revisiting optimal decoding for machine translation IBM model 4
Sebastian Riedel, James Freeman Clarke · 2009
This paper revisits optimal decoding for statistical machine translation using IBM Model 4. We show that exact/optimal inference using Integer Linear Programming is more practical than previously suggested when used in conjunction with the Cutting-Plane Algorithm. In our experiments we see that exact inference can provide a gain of up to one BLEU point for sentences of length up to 30 tokens.