Entity recognition in the biomedical domain using a hybrid approach

Table 6 Performance of the presented systems in a CR evaluation, compared to results reported in [24]

System	Precision	Recall	F1
OGER	0.32	0.52	0.40
OGER+Distiller NN	0.51	0.49	0.50
OGER+Distiller CRF	0.49	0.29	0.37
MMTx	0.43	0.40	0.42
MGrep	0.48	0.12	0.19
Concept Mapper	0.48	0.34	0.40
cTakes Dictionary Lookup	0.51	0.43	0.47
cTakes Fast Lookup	0.41	0.40	0.41
NOBLE Coder	0.44	0.43	0.43

Please note that, as stated in the “Concept recognition” section, the systems described in [24] are evaluated on the whole corpus, while we use 20 documents for testing and the remainder for training. The best values are highlighted in boldface

ISSN: 2041-1480