Skip to main content

Table 3 Evaluation results of the baseline methods using the fruit-fly dataset

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

Method

Precision

Recall

Accuracy

F1 score

baseline1 (14 strings)

0.79

0.40

0.82

0.53

baseline2 (15 strings)

0.95

0.43

0.85

0.60