Concept recognition as a machine translation problem

BMC Bioinformatics

Table 16 Exact match results for the unseen and seen text mentions (relative to the training data) for the core evaluation annotation set of the 30 held-out documents

Ontology	Total/unique # unseen mentions	% Unseen OpenNMT class ID (%)	% Seen OpenNMT class ID (%)	% Unseen OpenNMT character (%)	% Seen OpenNMT character (%)
ChEBI	345/148	17	94	69	99
CL	774/208	39	98	92	> 99
GO_BP	727/367	17	98	65	99
GO_CC	301/85	29	99	67	> 99
GO_MF	3/3	33	> 99	70	> 99
MOP	18/7	83	98	96	> 99
NCBITaxon	81/52	0	89	72	98
PR	2926/388	0	19	71	80
SO	181/105	62	99	89	> 99
UBERON	1584/514	20	97	80	99

Reporting the total number of mentions and the number of unique mentions along with the percent exact match on the class ID level and character level for both unseen and seen text mentions

ISSN: 1471-2105