Table 4 Performance (in %) of the relation extraction system on the test set of the ADE corpus for different sizes of the training set
From: Knowledge-based extraction of adverse drug events from biomedical text
Abstracts for training | Precision | Recall | F-score |
|---|---|---|---|
50 | 38.1 | 74.8 | 50.5 |
100 | 39.8 | 75.2 | 52.1 |
200 | 41.1 | 75.7 | 53.3 |
400 | 42.1 | 76.3 | 54.3 |