performance_report.md

Performance on Training Set

Span Level

Label	Precision	Recall	F1-score	Support
Chemical	0.996	0.989	0.993	5184
Disease	0.983	0.972	0.977	4280
macro avg	0.989	0.981	0.985	9464
weighted avg	0.990	0.982	0.986	9464

Token Level

Label	Precision	Recall	F1-score	Support
O	1.000	0.999	1.000	106678
B-Chemical	0.999	0.997	0.998	5185
I-Chemical	0.997	1.000	0.998	6871
B-Disease	0.997	0.997	0.997	4230
I-Disease	0.993	0.997	0.995	4663
macro avg	0.997	0.998	0.998	127627
weighted avg	0.999	0.999	0.999	127627

Performance on Validation Set

Span Level

Label	Precision	Recall	F1-score	Support
Chemical	0.949	0.947	0.948	5326
Disease	0.837	0.844	0.840	4354
macro avg	0.893	0.896	0.894	9680
weighted avg	0.899	0.901	0.900	9680

Token Level

Label	Precision	Recall	F1-score	Support
O	0.990	0.986	0.988	105898
B-Chemical	0.968	0.962	0.965	5323
I-Chemical	0.941	0.969	0.955	6639
B-Disease	0.887	0.900	0.893	4299
I-Disease	0.848	0.872	0.860	4725
macro avg	0.927	0.938	0.932	126884
weighted avg	0.978	0.977	0.977	126884

Performance on Testing Set

Span Level

Label	Precision	Recall	F1-score	Support
Chemical	0.927	0.925	0.926	5370
Disease	0.815	0.862	0.838	4486
macro avg	0.871	0.893	0.882	9856
weighted avg	0.876	0.896	0.886	9856

Token Level

Label	Precision	Recall	F1-score	Support
O	0.990	0.981	0.986	113619
B-Chemical	0.950	0.948	0.949	5346
I-Chemical	0.900	0.971	0.934	6419
B-Disease	0.852	0.901	0.876	4456
I-Disease	0.823	0.874	0.848	4759
macro avg	0.903	0.935	0.918	134599
weighted avg	0.974	0.973	0.973	134599