Chinese Named Entity Recognition On Ontonotes

Métriques

F1

Precision

Recall

Résultats

Résultats de performance de divers modèles sur ce benchmark

				Paper Title
BERT-MRC+DSC	84.47	-	-	Dice Loss for Data-imbalanced NLP Tasks
W2NER	83.08	-	-	Unified Named Entity Recognition as Word-Word Relation Classification
Baseline + BS	82.83	-	-	Boundary Smoothing for Named Entity Recognition
BERT-MRC	82.11	-	-	A Unified MRC Framework for Named Entity Recognition
FGN	82.04	-	-	FGN: Fusion Glyph Network for Chinese Named Entity Recognition
FLAT+BERT	81.82	-	-	FLAT: Chinese NER Using Flat-Lattice Transformer
AESINER	81.18	-	-	Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information
Glyce + BERT	80.62	81.87	81.4	Glyce: Glyph-vectors for Chinese Character Representations
SLK-NER	80.2	-	-	SLK-NER: Exploiting Second-order Lexicon Knowledge for Chinese NER
NFLAT	77.21	75.17	79.37	NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition
FLAT	76.45	-	-	FLAT: Chinese NER Using Flat-Lattice Transformer
LSTM + Lexicon augment	75.54	-	-	Simplify the Usage of Lexicon in Chinese NER
LGN	74.89	76.13	73.68	A Lexicon-Based Graph Neural Network for Chinese NER
Lattice	73.88	-	-	Chinese NER Using Lattice LSTM
CAN-NER Model	73.64	75.05	72.29	CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition

0 of 15 row(s) selected.