keras_cnn_gru: keras cnn gru
In systats/textlearnR:

Word embedding + 1D pooled convolution + gru layer

keras_cnn_gru(input_dim, embed_dim = 128, seq_len = 50,
  filter_size = 5, n_filters = 100, pool_size = 4, gru_dim = 64,
  gru_drop = 0.2, bidirectional = F, output_dim = 2,
  output_fun = "softmax")

`input_dim`	Number of unique vocabluary/tokens
`embed_dim`	Number of word vectors
`seq_len`	Length of the input sequences
`filter_size`	the window size (kernel_size)
`n_filters`	the number of convolutional filters
`pool_size`	pooling dimension (filters)
`gru_dim`	Number of lstm neurons (default 32)
`gru_drop`	default is 2
`bidirectional`	default is F
`output_dim`	Number of neurons of the output layer
`output_fun`	Output activation function