Table 5.

The performances of different models in the test set of self-built corpus.

Model	%		F1
	P	R
BERT-Bi-LSTM-CRF	64.71		91.67	75.86
BERT-FLAT-Lattice-Transformer	62.61		72.02	67.09
SSBC	70.52		85.91	77.46
Bichar-SSBC	71.47		86.58	78.30
BERT-SSBC	73.24		87.25	79.63
The bold font denotes the best result for each column