Skip to main content

Table 6 The effect of additional features on our development sets

From: A neural network approach to chemical and gene/protein entity recognition in patents

Model CEMP Dev GPRO Dev
Precision Recall F-score Precision Recall F-score
Baseline 87.58 92.50 89.97 67.97 86.06 75.95
+ POS feature 88.12 91.70 89.87 − 0.10 68.72 85.46 76.18 +0.23
+ Chunking feature 87.21 92.58 89.81 − 0.16 67.21 87.45 76.01 +0.06
+ NER feature 87.57 91.81 89.64 − 0.33 69.32 84.72 76.25 +0.30
+ All features 87.97 91.39 89.65 − 0.32 70.84 83.76 76.76 +0.81
  1. Italic values denote the highest values