Table 3 The details of parameter adjustment

Learning-rate

The initial learning rate of optimizer

{0.001,0.002,0.005,0.01,0.02,0.05}

0.001

Hidden1

The embedding dimension of layer 1

{16,32,64,128,256}

256

Hidden2

The embedding dimension of layer 2

{16,32,64,128,256}

128

Dropout

The dropout rate of nodes

{0,0.2,0.4,0.5}

0