Skip to main content

Table 3 Results with KF/ELMo representations on the test set for PNER

From: Knowledge-enhanced biomedical named entity recognition and normalization: application to proteins and genes

ModelStrict MatchOverlap Match
PRF1PRF1
Baseline0.7490.8160.7810.8000.8710.834
+ linguistic features0.8170.7640.7890.8680.8120.839
+ linguistic features + KFs0.7760.8450.8090.8200.8930.855
+ linguistic features + ELMo0.8260.8010.8130.8740.8470.860
+ linguistic features + KFs + ELMo (ours)0.8150.8120.8140.8730.8690.871
  1. Strict match criteria require that the predicted entity and the gold standard annotations have to match exactly at the byte offset; and overlap match criteria allows a match if the predicted entity overlaps with the gold annotation at all. The highest scores are highlighted in bold. We tune the hyper-parameters through the validation set and use the official evaluation script to assess the performance of the final chosen model on the test set