Skip to main content

Table 22 Exact match results for the concept normalization experiments on the core evaluation annotation set of 30 held-out documents (character level)

From: Concept recognition as a machine translation problem

Ontology

Token-ids (%)

Type-ids (%)

Shuffled-ids (%)

Random-ids (%)

Alphabetical-ids (%)

ChEBI

94*

89

60

58

94*

CL

92*

92*

86

80

65

GO_BP

93*

91

85

56

84

GO_CC

91

92*

92*

89

82

GO_MF

99*

99*

99*

99*

94

MOP

99

> 99*

99

99

86

NCBITaxon

97*

74

73

68

74

PR

76*

75

40

30

74

SO

99*

99*

99*

98

96

UBERON

95*

93

69

54

88

  1. We report the exact match percentage at the character level. The highest percentage is bolded and with an asterisk*
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us