Table 4.

P values of the different models for the National Center for Biotechnology Information disease corpus.

Model	Model, P value
	BERTa	EhrBERT500kb	EhrBERT1Mc	BioBERT
DNormd	.10	.01	.04	.004
BERT		.25	.15	.03
EhrBERT500k			.37	.09
EhrBERT1M				.32

^aBERT: bidirectional encoder representations from transformers.

^bEhrBERT_500k: BERT-based model that was trained using 500,000 electronic health record notes.

^cEhrBERT_1M: BERT-based model that was trained using 1 million electronic health record notes.

^dDNorm: disease name normalization.