Skip to main content

Table 2 Development results Development results for the various hedge classifiers tested by 10-fold cross-validation on the biomedical abstracts and articles in the training data.

From: Predicting speculation: a simple disambiguation approach to hedge detection in biomedical literature

  Sentence Level Token Level
Model Prec Rec F1 Prec Rec F1
91.01 86.53 88.69 90.60 71.03 79.59
C WbW 94.31 88.30 91.19 94.67 81.89 87.80
C Disamb 93.64 89.68 91.60 94.01 83.55 88.45
93.78 88.45 91.03 94.05 81.97 87.58