Research Article
A Novel Sample Selection Strategy for Imbalanced Data of Biomedical Event Extraction with Joint Scoring Mechanism
Table 9
Results of the proposed method on GE’13 test set.
| | Event class | Event type | | | |
| | SVT | Gene_expression | 82.88 | 79.91 | 81.36 | | Transcription | 52.48 | 65.43 | 58.24 | | Protein_catabolism | 64.29 | 50.00 | 56.25 | | Phosphorylation | 81.25 | 76.02 | 78.55 | | Localization | 31.31 | 83.78 | 45.59 | | Total | 74.12 | 77.56 | 75.80 |
| | BIND | Binding | 39.34 | 44.11 | 41.59 |
| | REG | Regulation | 23.61 | 39.08 | 29.44 | | Positive_regulation | 39.56 | 46.71 | 42.84 | | Negative_regulation | 39.73 | 46.24 | 42.74 | | Total | 37.24 | 45.74 | 41.05 |
| | ALL total | 48.65 | 56.24 | 52.17 |
|
|
Performance is shown in recall (), precision (), and -score ().
|