Generation of word graphs in statistical machine translation

Nicola Ueffing, Franz Josef Och, Hermann Ney · 2002

Statistical machine translation systems usually compute the single sentence that has the highest probability according to the models that are trained on data. We describe a method for constructing a word graph to represent alternative hypotheses in an efficient way. The advantage is that these hypotheses can be rescored using a refined language or translation model. Results are presented on the German-English Verbmobil corpus.

Read the paper · More papers on PaperTik