TCM Prescription Generation via Knowledge Source Guidance Network Combined with Herbal Candidate Mechanism

Table 1

Performance comparison of the baseline models with our model (GSCCAM) for automatic quantitative evaluation.

Models	Precision	Recall	F1-score
KDHR [18]	0.2041	0.1473	0.1711
PTM [21]	0.1982	0.1536	0.1731
Coverage-Soft-Model [44]	0.1844	0.1073	0.1357
Herb-Know [24]	0.3082	0.2101	0.2499
TPGen [23]	0.2794	0.2291	0.2518
GSCCAM	0.3739	0.2504	0.2999