Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER
Open paper
Benchmark
Model
Rank
Results
named-entity-recognition-ner-on-ontonotes-v5
Att-BiLSTM-CNN
#20
F1: 88.4
Precision: 88.71
Recall: 88.11
named-entity-recognition-on-wnut-2017
Cross-BiLSTM-CNN
#17
F1: 42.85
Precision: 58.28
Recall: 33.92
Rank counts only results with a code link.