Skip to main content

Table 4 Effect of individual stop-word lists on F-score.

From: Recognition of chemical entities: combining dictionary-based and grammar-based approaches

 

Baseline

Basic English

PubMed stop words

Jochem stop words

CHEMDNER guidelines

Resource

P

R

F

P

R

F

P

R

F

P

R

F

P

R

F

ChEBI

28.3

40.6

33.4

69.0

40.3

50.9

63.0

40.3

49.2

28.5

40.1

33.3

29.3

40.6

34.0

ChEMBL

87.9

18.7

30.8

87.9

18.7

30.8

87.9

18.7

30.8

88.8

18.7

30.9

87.9

18.7

30.8

ChemSpider

65.4

39.0

48.9

74.4

38.8

51.0

65.3

38.8

48.7

69.3

38.6

49.6

67.9

39.0

49.5

DrugBank

63.0

17.2

27.0

63.0

17.2

27.0

63.0

17.2

27.0

78.1

17.1

28.1

63.1

17.2

27.0

HMDB

53.2

34.5

41.8

74.6

34.4

47.1

72.6

34.4

46.7

55.7

34.0

42.2

55.2

34.5

42.5

NPC

46.8

26.7

34.0

47.6

26.5

34.0

46.6

26.5

33.7

52.2

26.7

35.3

53.3

26.7

35.6

TTD

43.9

14.7

22.1

64.9

14.5

23.7

66.0

14.5

23.8

50.6

14.7

22.8

43.9

14.7

22.1

PubChem

17.4

59.0

26.9

44.5

58.7

50.6

42.4

58.6

49.2

18.9

58.3

28.5

17.9

59.0

27.4

Jochem

64.2

52.5

57.8

65.2

52.5

58.2

64.2

52.5

57.8

64.1

52.5

57.7

67.1

52.5

58.9

UMLS

37.7

51.1

43.4

45.4

50.8

43.6

38.0

51.1

43.6

40.0

50.8

44.9

42.4

51.1

46.4

ChEBI

10.4

16.6

12.8

21.0

16.6

18.5

21.0

16.6

18.5

10.8

16.4

13.1

11.6

16.6

13.7

Family Oscar

25.1

63.2

35.9

25.4

63.0

36.2

25.3

62.9

36.1

25.7

62.7

36.4

27.7

63.2

38.5

LeadMine

64.9

47.4

54.8

66.4

47.4

55.3

64.9

47.4

54.8

68.0

47.1

55.7

72.8

47.4

57.4

ChemAxon

80.9

41.8

55.1

80.9

41.8

55.1

80.9

41.8

55.1

81.1

41.7

55.1

83.3

41.8

55.5