Table 1.
Evaluation scores obtained for the DDI detection task on the DDI corpus and on each type of document, comparing different configurations of the model
| DDI test | DrugBank | Medline | |||||||
|---|---|---|---|---|---|---|---|---|---|
| Configuration | P | R | F | P | R | F | P | R | F |
| Word embeddings | 0.7551 | 0.6865 | 0.7192 | 0.7620 | 0.7158 | 0.7382 | 0.6389 | 0.377 | 0.4742 |
| + WordNet | 0.716 | 0.6936 | 0.7046 | 0.7267 | 0.7143 | 0.7204 | 0.5800 | 0.4754 | 0.5225 |
| + Common Ancestors | 0.7661 | 0.6738 | 0.7170 | 0.7723 | 0.7003 | 0.7345 | 0.6667 | 0.3607 | 0.4681 |
| + Concat. Ancestors | 0.7078 | 0.7489 | 0.7278 | 0.7166 | 0.7578 | 0.7366 | 0.6032 | 0.623 | 0.6129 |
| + WordNet + Ancestors | 0.6572 | 0.8184 | 0.7290 | 0.6601 | 0.8385 | 0.7387 | 0.5574 | 0.5574 | 0.5574 |
Evaluation metrics used: Precision (P), Recall (R) and F1-score (F). Each row represents the addition of an information source to the initial configuration
Boldface indicates the configuration with highest score for each measure