Few Shot Ner On Few Nerd Intra

Métriques

10 way 1~2 shot

10 way 5~10 shot

5 way 1~2 shot

5 way 5~10 shot

Résultats

Résultats de performance de divers modèles sur ce benchmark

					Paper Title
JCELRNER	-	-	62.49±0.43	71.62±0.44	-
NuNER	57.63±0.38	62.99±0.27	62.48±0.28	69.16±0.28	NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data
TadNER	55.44±0.08	60.87±0.22	60.78±0.32	67.94±0.17	Type-Aware Decomposed Framework for Few-Shot Named Entity Recognition
MSDP	47.13±0.69	64.69±0.51	56.35±0.28	66.80±0.78	A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER
HEProto	46.45±0.21	58.98±0.22	53.03±0.30	65.70±0.21	HEProto: A Hierarchical Enhancing ProtoNet based on Multi-Task Learning for Few-shot Named Entity Recognition
DecomposedMetaSL	43.03±0.29	57.58±0.26	49.90±0.33	64.36±0.20	Decomposed Meta-Learning for Few-Shot Sequence Labeling
DecomposedMetaNER	42.84±0.46	57.31±0.25	49.48±0.85	62.92±0.57	Decomposed Meta-Learning for Few-Shot Named Entity Recognition
BERT-SparseLT+CONTainNER	40.48	53.04	47.20	59.67	Language Model Pre-Training with Sparse Latent Typing
CONTaiNER	33.84	47.49	40.43	53.70	CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning
ESD	30.00±0.70	42.15±2.60	36.08±1.60	52.14±1.50	An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labeling
StructShot	21.03±1.13	26.42±0.60	30.21±0.90	38.00±1.29	Few-NERD: A Few-Shot Named Entity Recognition Dataset
NNShot	18.27±0.41	27.38±0.53	25.78±0.91	36.18±0.79	Few-NERD: A Few-Shot Named Entity Recognition Dataset
ProtoBERT	15.05±0.44	35.40±0.13	20.76±0.84	42.54±0.94	Few-NERD: A Few-Shot Named Entity Recognition Dataset

0 of 13 row(s) selected.

Few Shot Ner On Few Nerd Intra | SOTA | HyperAI