Skip to main content

Table 5 Evaluation results from our system using IG weighting on the fruit-fly dataset

From: Recognizing speculative language in biomedical research articles: a linguistically motivated perspective

Threshold Precision Recall Accuracy F1 score
1 0.66 0.89 0.86 0.76
1.5 0.81 0.79 0.90 0.80
2 0.83 0.69 0.89 0.75
3 0.88 0.53 0.87 0.66
5 0.98 0.25 0.81 0.40
6 1 0.13 0.79 0.24