Relation Extraction On Tacred

평가 지표

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	F1	Paper Title	Repository
DeepStruct multi-task w/ finetune	76.8	DeepStruct: Pretraining of Language Models for Structure Prediction
TRE	67.4	Improving Relation Extraction by Pre-trained Language Representations
SA-LSTM+D	67.6	Beyond Word Attention: Using Segment Attention in Neural Relation Extraction	-
C-AGGCN	68.2	Attention Guided Graph Convolutional Networks for Relation Extraction
LUKE	-	LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention
K-ADAPTER (F+L)	72.04	K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
C-GCN	66.4	Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
RoBERTa-large-typed-marker	74.6	An Improved Baseline for Sentence-level Relation Extraction
C-GCN + PA-LSTM	68.2	Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
KEPLER	71.7	KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
AGGCN	65.1	Attention Guided Graph Convolutional Networks for Relation Extraction
RE-MC	75.4	Enhancing Targeted Minority Class Prediction in Sentence-Level Relation Extraction
ERNIE	67.97	ERNIE: Enhanced Language Representation with Informative Entities
C-SGC	67.0	Simplifying Graph Convolutional Networks
RECENT+SpanBERT	75.2	Relation Classification with Entity Type Restriction	-
SpanBERT-large	70.8	SpanBERT: Improving Pre-training by Representing and Predicting Spans
NLI_RoBERTa	71.0	Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction
KnowBert-W+W	71.5	Knowledge Enhanced Contextual Word Representations
LLM-QA4RE (XXLarge)	52.2	Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors
Contrastive Pre-training	69.5	Learning from Context or Names? An Empirical Study on Neural Relation Extraction

0 of 40 row(s) selected.