A Data-Driven Model for Automated Chinese Word Segmentation and POS Tagging

Table 4

Key parameters of the automation model.

Parameter	Numerical value
Number of AlexNet hidden layer nodes	200
AlexNet network depth	2
Number of AlexNet convolutional layers (pooling layers)	3
Dropout	0.2
Training optimiser	AdaGrad
Initial learning rate	0.1
Batch size	32
Word vector dimension	64