Table 1 Statistics of CCKS2017_CNER and ICRC_CNER for entity recognition in Chinese clinical text
From: Entity recognition in Chinese clinical text using attention-based CNN-LSTM-CRF
Dataset (CCKS2017_CNER) | #Record | #Clinical Entity | |||||
#Body | #Disease | #Symptom | #Test | #Treament | #All | ||
Training (300) | 300 | 10,719 | 722 | 7831 | 9546 | 1048 | 29,866 |
Test (100) | 100 | 3021 | 553 | 2311 | 3143 | 465 | 9493 |
Total (400) | 400 | 13,740 | 1275 | 10,142 | 12,689 | 1513 | 39,359 |
Dataset (ICRC_CNER) | #Record | #Clinical Entity | |||||
#Medication | #Disease | #Symptom | #Test | #Treament | #All | ||
Training | 600 | 1293 | 11,470 | 5270 | 17,024 | 3065 | 38,122 |
0 | 7441 | 75 | 7 | 107 | 7630 | ||
Development | 176 | 475 | 3594 | 1738 | 5276 | 938 | 12,021 |
0 | 2421 | 37 | 3 | 41 | 2502 | ||
Test | 400 | 999 | 7932 | 3353 | 11,326 | 2020 | 35,630 |
3 | 5153 | 57 | 6 | 61 | 5280 | ||
Total | 1176 | 2767 | 22,996 | 10,361 | 33,626 | 6023 | 75,773 |
3 | 15,015 | 169 | 16 | 209 | 15,412 | ||