Table 2 Precision, recall and F1-Score results for the training, development and evaluation set including the number at the document level of true positives (TP), false positives (FP) and false negatives (FN)
TP | FP | FN | Precision (%) | Recall (%) | F1-Score (%) | |
|---|---|---|---|---|---|---|
Training set | 75 | 4 | 2 | 94.9 | 97.4 | 96.1 |
Development | 62 | 6 | 3 | 91.1 | 95.3 | 93.1 |
Evaluation set | 72 | 5 | 7 | 93.5 | 91.1 | 92.2 |