BioByGANS: biomedical named entity recognition by fusing contextual and syntactic features through graph attention network in node classification framework

Table 1 Statistics of the biomedical datasets

Entity type	Corpus name	Annotated sentences	Sentence max length
Gene/Protein	BC2GM	20,130	206
	JNLPBA	22,401	221
Species	Species-800	8193	143
	LINNAEUS	23,151	246
Disease	BC5CDR-Disease	13,938	225
	NCBI-Disease	7287	123
Chemical	BC4CHEMD	87,674	225
	BC5CDR-Chemical	13,938	225

ISSN: 1471-2105