Table 5:

Performance of the best performing model (i.e., RoBERTa-MIMIC-Trial) by entity types on Chia.

Model	Strict Criterion			Relaxed Criterion
	Precision	Recall	F1	Precision	Recall	F1
Overall	0.6209	0.6993	0.6578	0.7662	0.8333	0.7984
Condition	0.7324	0.7878	0.7591	0.8721	0.9144	0.8928
Device	0.4667	0.6829	0.5545	0.6167	0.8293	0.7073
Drug	0.6949	0.7910	0.7398	0.8418	0.9100	0.8746
Measurement	0.6127	0.6893	0.6487	0.7937	0.8464	0.8192
Mood	0.2727	0.2449	0.2581	0.3636	0.3265	0.3441
Observation	0.2933	0.2444	0.2667	0.4333	0.3556	0.3906
Person	0.6914	0.8643	0.7683	0.7257	0.8929	0.8007
Pregnancy_considerations	0.0000	0.0000	0.0000	0.3784	0.4444	0.4088
Procedure	0.5012	0.6375	0.5612	0.6560	0.8031	0.7222
Temporal	0.4800	0.6316	0.5455	0.6514	0.8008	0.7184
Value	0.7000	0.7278	0.7136	0.8324	0.8685	0.8500