Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER

29 Aug 2019Peng-Hsuan LiTsu-Jui FuWei-Yun Ma

BiLSTM has been prevalently used as a core module for NER in a sequence-labeling setup. State-of-the-art approaches use BiLSTM with additional resources such as gazetteers, language-modeling, or multi-task supervision to further improve NER... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Named Entity Recognition Long-tail emerging entities Cross-BiLSTM-CNN F1 42.85 # 3
Named Entity Recognition Ontonotes v5 (English) Att-BiLSTM-CNN F1 88.4 # 8