Relation Classification on TACRED

Metric: F1 (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

#	Model↕	F1▼	Extra Data	Paper	Date↕	Code
1	DeepStruct multi-task w/ finetune	76.8	No	DeepStruct: Pretraining of Language Models for S...	2022-05-21	Code
2	DeepEx (zero-shot top-10)	76.4	No	Zero-Shot Information Extraction as a Unified Te...	2021-09-23	Code
3	DeepStruct multi-task	74.9	No	DeepStruct: Pretraining of Language Models for S...	2022-05-21	Code
4	LUKE 483M	72.7	No	LUKE: Deep Contextualized Entity Representations...	2020-10-02	Code
5	K-Adapter	72	No	K-Adapter: Infusing Knowledge into Pre-Trained M...	2020-02-05	Code
6	TANL	71.9	No	Structured Prediction as Translation between Aug...	2021-01-14	Code
7	KEPLER	71.7	No	KEPLER: A Unified Model for Knowledge Embedding ...	2019-11-13	Code
8	MTB Baldini Soares et al. (2019)	71.5	No	Matching the Blanks: Distributional Similarity f...	2019-06-07	Code
9	KnowBERT	71.5	No	Knowledge Enhanced Contextual Word Representations	2019-09-09	Code
10	RoBERTa	71.3	No	K-Adapter: Infusing Knowledge into Pre-Trained M...	2020-02-05	Code
11	SpanBERT	70.8	No	SpanBERT: Improving Pre-training by Representing...	2019-07-24	Code
12	ERNIE	68	No	ERNIE: Enhanced Language Representation with Inf...	2019-05-17	Code
13	C-GCN	66.4	No	Graph Convolution over Pruned Dependency Trees I...	2018-09-26	Code
14	BERT	66	No	ERNIE: Enhanced Language Representation with Inf...	2019-05-17	Code
15	TANL (multi-task)	61.9	No	Structured Prediction as Translation between Aug...	2021-01-14	Code
16	DeepEx (zero-shot top-1)	49.2	No	Zero-Shot Information Extraction as a Unified Te...	2021-09-23	Code
17	Deepstruct zero-shot	36.1	No	DeepStruct: Pretraining of Language Models for S...	2022-05-21	Code