Skip to main content

Table 3 Comparisons of perplexities on test set of five million training corpus with different sizes of class layer

From: RNN language model with word clustering and class-based output layer

Class RNNLM-Freq / +KN5 RNNLM-Brown / +KN5
50 218.13 / 178.10 206.19 / 172.08
100 220.47 / 178.50 208.37 / 172.06
200 219.60 / 178.21 206.54 / 171.21
400 219.73 / 178.09 205.02 / 170.56
  1. Perplexity of LM-KN5 with the same training text (five million words) on test set is 231.02.