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 used " -ukndiscount -interpolate" as the smoothing parameter.


Jin'ichi Murakami 平成22年7月5日