Table 5.

The hyper-parameters of the proposed CNN based on the default mode.

Hyper-parameter	Value
Input length	$L_{\mathit{max}}$
Batch size	64
Embedding layer	$L_{\mathit{max}}\times 300$, Trainable = False,
	Num_Channels = 1
Convolution blocks	$[2,3,4]$, $128\times 3$, ReLu
Pooling blocks	Max-pooling
Fully connected layer units	$128\times 3$
Regularization	L2
Learning rate	0.001 with decay rate 0.9
Optimizer	Adam