Research Article

TCMNER and PubMed: A Novel Chinese Character-Level-Based Model and a Dataset for TCM Named Entity Recognition

Table 4

The number of entities of 5 classes.

DatasetNumber of entitiesNumber of samples
Clinical manifestationSyndromeDiseaseTreatment lawHerbTotal

Publications18,1509,0431,32710,6989,68948,90779579
Medical records75,17737,0531,4289,96857,836181,46214801