Table 2 Distribution of labels in the SPACCC dataset
From: Combining word embeddings to extract chemical and drug entities in biomedical literature
Train | Dev | Test | |
|---|---|---|---|
NORMALIZABLES | 2304 | 1121 | 973 |
NO_NORMALIZABLES | 24 | 16 | 10 |
PROTEINAS | 1405 | 745 | 859 |
UNCLEAR | 89 | 44 | 34 |