Skip to main content

Table 9 Results of BERT systems for entity classification on PharmaCoNER test dataset

From: Analyzing transfer learning impact in biomedical cross-lingual named entity recognition and normalization

System

Precision (%)

Recall (%)

F-score (%)

bert-base-multilingual-cased

84.01

76.91

80.23

BETO cased

84.68

79.02

81.66

SBC-BERT

87.88

89.74

88.80

  1. Bold values are the best results for Precision (P), Recall (R) and F-score
Back to article page