Table 1.

Descriptive statistics of the medical named entity recognition datasets.

Dataset	Medical entity type	Entity types, n	Annotations, n
Revised JNLPBAa	DNA, RNA, protein, cell line, and cell type	5	52,785
BC5CDRb	Disease and chemical	2	38,596
AnatEMc	Organism subdivision, anatomical system, organ, multi-tissue structure, tissue, cell, developing anatomical structure, cellular component, organism substance, immaterial anatomical entity, pathological formation, and cancer	12	11,562

^aJNLPBA: Joint Workshop on Natural Language Processing in Biomedicine and its Applications.

^bBC5CDR: BioCreative V CDR.

^cAnatEM: Anatomical Entity Mention.