next up previous
次へ: Decoder 上へ: Experiments with our Machine 戻る: "ENGLISH"-"English" Phrase Tables

$ 5$ -gram Language Model

We calculated the $ 5$ -gram model using ngram-count in the Stanford Research Institute Language Model (SRILM) toolkit [6]. And We did not smooth parameters, it means we set the smoothing parameter as ``-cdiscount 0''.


平成24年1月18日