Clinical Named Entity Recognition from Chinese Electronic Medical Records Based on Deep Learning Pretraining

Table 3

Comparison results of different dimensions.

Different dimensions	Marco-P (%)	Marco-R (%)	Marco-F1 (%)
Random embedding	69.52	69.70	69.38
50 embeddings	53.42	54.31	53.74
150 embeddings	72.48	72.54	72.51
300 embeddings	55.36	61.03	57.88