Table 2. Comparison with state of the art systems: Neji, NCBO Annotator, MetaMap, ConceptMapper.

Ontology	Neji			NCBO Annotator			MetaMap			ConceptMapper			Our best result
	P	R	F1	P	R	F1	P	R	F1	P	R	F1	P	R	F1
CL	0.63	0.65	0.64	0.76	0.20	0.32	0.61	0.80	0.69	0.88	0.78	0.83	0.85	0.72	0.78
GO_CC	0.75	0.66	0.70	0.75	0.27	0.40	0.67	0.73	0.70	0.92	0.66	0.77	0.84	0.73	0.78
GO_BPMF	0.44	0.29	0.35	-	-	-	-	-	-	-	-	-	0.48	0.34	0.40
ChEBI	0.49	0.36	0.33	0.70	0.46	0.56	0.36	0.50	0.42	0.55	0.56	0.56	0.48	0.55	0.51
PRO	0.46	0.39	0.42	0.49	0.51	0.50	0.39	0.34	0.36	0.57	0.57	0.57	0.42	0.53	0.47
SO	-	-	-	0.63	0.33	0.44	0.47	0.54	0.50	0.56	0.57	0.56	0.51	0.52	0.52

Bolded values denote the best F-Score across all methods. ConceptMapper outperforms all approaches on all ontologies. Our method achieves an increased efficiency against the other three systems on three ontologies: CL, GO_CC and SO, in addition to outperforming Neji on GO_BPMF