TOKENS | Train | Dev | Test |
---|---|---|---|
Abstracts | 84 855 | 27 957 | 28 433 |
M (SD) | 282.85 (±67.66) | 279.57 (±56.34) | 284.33 (±88.49) |
EudraCT | 90 348 | 30 713 | 29 867 |
M (SD) | 215.11 (±66.93) | 219.38 (±68.04) | 213.34 (±77.81) |
All | 175 203 | 58 670 | 58 300 |
M (SD) | 243.34 (±75.04) | 244.46 (±69.94) | 242.92 (±89.41) |
ENTITIES | Train | Dev | Test |
Abstracts | 12 129 | 4092 | 3810 |
M (SD) | 40.43 (±13.29) | 40.92 (±13.78) | 38.10 (±14.63) |
EudraCT | 15 972 | 5537 | 5159 |
M (SD) | 38.03 (±14.10) | 39.55 (±14.70) | 36.85 (±14.90) |
All | 28 101 | 9629 | 8969 |
M (SD) | 39.03 (±13.81) | 40.12 (±14.31) | 37.37 (±14.77) |
ANAT | 4023 | 1442 | 1263 |
M (SD) | 5.59 (±4.88) | 6.01 (±4.78) | 5.26 (±4.61) |
CHEM | 5577 | 1840 | 1807 |
M (SD) | 7.75 (±6.00) | 7.67 (±6.01) | 7.53 (±6.50) |
DISO | 7832 | 2716 | 2519 |
M (SD) | 10.88 (±6.18) | 11.32 (±6.94) | 10.50 (±6,01) |
PROC | 10 669 | 3631 | 3380 |
M (SD) | 14.82 (±6.91) | 15.13 (±7.41) | 14.08 (±7.27) |