Skip to main content

Table 4 Evaluation results from our system using SA 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 0.68 0.95 0.88 0.79
2 0.74 0.94 0.90 0.83
3 0.85 0.86 0.93 0.85
4 0.91 0.71 0.91 0.80
5 0.92 0.63 0.89 0.75
6 0.97 0.40 0.85 0.57
7 1 0.19 0.79 0.33