Named Entity Recognition in Chinese Medical Literature Using Pretraining Models

Table 4

Recognition results of original dataset and augmented dataset.

	P (%)	R (%)	F (%)
Models
BERT	90.778	90.674	90.726
ERNIE	90.488	90.354	90.421
ERNIE-tiny	89.361	89.162	89.261
Models (augmented dataset)
BERT	90.968	91.048	91.008
ERNIE	90.659	90.527	90.593
ERNIE-tiny	89.466	89.348	89.407