Skip to main content

Table 5 The distribution of chemical entities with different lengths in the CHEMDNER corpus.

From: Enhancing of chemical compound and drug name recognition using representative tag scheme and fine-grained tokenization

Entity Length

Training (%)

Development (%)

Test (%)

Overall (%)

1

70.50

70.82

71.45

70.90

2

9.33

9.29

8.99

9.21

3

6.28

6.12

6.28

6.22

4

4.63

4.43

4.06

4.39

≦4

90.73

90.66

90.79

90.72

4 <

9.27

0.34

9.21

9.28