Relation Extraction On Semeval 2010 Task 8

평가 지표

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	F1	Paper Title	Repository
SpanBERT	88.8	SPOT: Knowledge-Enhanced Language Representations for Information Extraction	-
KLG	90.5	Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extraction	-
CorefBERT	89.2	SPOT: Knowledge-Enhanced Language Representations for Information Extraction	-
BERTEM+MTB	89.5	Matching the Blanks: Distributional Similarity for Relation Learning
KnowPrompt	90.3	KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction
KnowBert-W+W	89.1	Knowledge Enhanced Contextual Word Representations
RoBERTa	88.7	SPOT: Knowledge-Enhanced Language Representations for Information Extraction	-
TRE	87.1	Improving Relation Extraction by Pre-trained Language Representations
SPOT	90.6	SPOT: Knowledge-Enhanced Language Representations for Information Extraction	-
RE-DMP + XLNet	89.90	Improving Relation Extraction through Syntax-induced Pre-training with Dependency Masking
KnowBERT	89.1	SPOT: Knowledge-Enhanced Language Representations for Information Extraction	-
LUKE	90.3	SPOT: Knowledge-Enhanced Language Representations for Information Extraction	-
Bi-LSTM	82.7	-	-
A-GCN + BERT	89.85	Dependency-driven Relation Extraction with Attentive Graph Convolutional Networks
SP	91.9	Relation Classification as Two-way Span-Prediction	-
CR-CNN	84.1	Classifying Relations by Ranking with Convolutional Neural Networks
Attention CNN	84.3	Attention-Based Convolutional Neural Network for Semantic Relation Extraction
REDN	91	Downstream Model Design of Pre-trained Language Model for Relation Extraction Task
Attention Bi-LSTM	84.0	-	-
Att-Pooling-CNN	88.0	-	-

0 of 31 row(s) selected.