From: Deep learning with language models improves named entity recognition for PharmaCoNER
Set | Training | Development | Test | Total |
---|---|---|---|---|
Documents | 500 | 250 | 250 | 1000 |
Sentences | 7003 | 3454 | 3403 | 13860 |
NORMALIZABLES | 2304 | 1121 | 973 | 4398 |
NO_NORMALIZABLES | 24 | 16 | 10 | 50 |
PROTEINAS | 1405 | 745 | 859 | 3009 |
UNCLEAR | 89 | 44 | 34 | 167 |