paper-with-me

Relation Classification 벤치마크

Relation Classification on TACRED

35개 결과 · ⬇ CSV · JSON

F1

36.1 49.58 63.05 76.53 90 2018-09 2026-09 C-GCN — 66.4 (2018-09-26) C-GCN — 66.4 (2018-09-26) BERT — 66.0 (2019-05-17) ERNIE — 68.0 (2019-05-17) BERT — 66.0 (2019-05-17) ERNIE — 68.0 (2019-05-17) MTB Baldini Soares et al. (2019) — 71.5 (2019-06-07) MTB Baldini Soares et al. (2019) — 71.5 (2019-06-07) SpanBERT — 70.8 (2019-07-24) SpanBERT — 70.8 (2019-07-24) KnowBERT — 71.5 (2019-09-09) KnowBERT — 71.5 (2019-09-09) KEPLER — 71.7 (2019-11-13) KEPLER — 71.7 (2019-11-13) RoBERTa — 71.3 (2020-02-05) K-Adapter — 72.0 (2020-02-05) RoBERTa — 71.3 (2020-02-05) K-Adapter — 72.0 (2020-02-05) LUKE 483M — 72.7 (2020-10-02) LUKE 483M — 72.7 (2020-10-02) TANL (multi-task) — 61.9 (2021-01-14) TANL — 71.9 (2021-01-14) TANL (multi-task) — 61.9 (2021-01-14) TANL — 71.9 (2021-01-14) DeepEx (zero-shot top-1) — 49.2 (2021-09-23) DeepEx (zero-shot top-10) — 76.4 (2021-09-23) DeepEx (zero-shot top-1) — 49.2 (2021-09-23) DeepEx (zero-shot top-10) — 76.4 (2021-09-23) Deepstruct zero-shot — 36.1 (2022-05-21) DeepStruct multi-task — 74.9 (2022-05-21) DeepStruct multi-task w/ finetune — 76.8 (2022-05-21) Deepstruct zero-shot — 36.1 (2022-05-21) DeepStruct multi-task — 74.9 (2022-05-21) DeepStruct multi-task w/ finetune — 76.8 (2022-05-21) Transformer Enhanced Relation Classifica — 90.0 (2025-09-14) C-GCN — 66.4 (2018-09-26) ERNIE — 68.0 (2019-05-17) MTB Baldini Soares et al. (2019) — 71.5 (2019-06-07) KEPLER — 71.7 (2019-11-13) K-Adapter — 72.0 (2020-02-05) LUKE 483M — 72.7 (2020-10-02) DeepEx (zero-shot top-10) — 76.4 (2021-09-23) DeepStruct multi-task w/ finetune — 76.8 (2022-05-21) Transformer Enhanced Relation Classifica — 90.0 (2025-09-14)
RankModel F1 PaperCodeYear
1 Transformer Enhanced Relation Classifica 자동 추출 90 Transformer Enhanced Relation Classification: A Comparative Analysis of Contextuality, Data Efficiency and Sequence Complexity 2025
2 Deepstruct zero-shot 36.1 DeepStruct: Pretraining of Language Models for Structure Prediction cgraywang/deepstruct 2022
3 DeepEx (zero-shot top-1) 49.2 Zero-Shot Information Extraction as a Unified Text-to-Triple Translation cgraywang/deepex 2021
4 TANL (multi-task) 61.9 Structured Prediction as Translation between Augmented Natural Languages amazon-science/tanl · amazon-research/tanl 2021
5 BERT 66.0 ERNIE: Enhanced Language Representation with Informative Entities thunlp/ERNIE · Mind23-2/MindCode-136 2019
6 C-GCN 66.4 Graph Convolution over Pruned Dependency Trees Improves Relation Extraction qipeng/gcn-over-pruned-trees 2018
7 ERNIE 68.0 ERNIE: Enhanced Language Representation with Informative Entities thunlp/ERNIE · Mind23-2/MindCode-136 2019
8 SpanBERT 70.8 SpanBERT: Improving Pre-training by Representing and Predicting Spans facebookresearch/SpanBERT · mandarjoshi90/coref · zixinzeng-jennifer/spanbert_trans · +3 2019
9 RoBERTa 71.3 K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters microsoft/K-Adapter · stevekgyang/sccl 2020
10 MTB Baldini Soares et al. (2019) 71.5 Matching the Blanks: Distributional Similarity for Relation Learning plkmo/BERT-Relation-Extraction · diffbot/knowledge-net · uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction · +10 2019
10 KnowBERT 71.5 Knowledge Enhanced Contextual Word Representations allenai/kb 2019
12 KEPLER 71.7 KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation THU-KEG/KEPLER 2019
13 TANL 71.9 Structured Prediction as Translation between Augmented Natural Languages amazon-science/tanl · amazon-research/tanl 2021
14 K-Adapter 72.0 K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters microsoft/K-Adapter · stevekgyang/sccl 2020
15 LUKE 483M 72.7 LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention huggingface/transformers · PaddlePaddle/PaddleNLP · studio-ousia/luke · +6 2020
16 DeepStruct multi-task 74.9 DeepStruct: Pretraining of Language Models for Structure Prediction cgraywang/deepstruct 2022
17 DeepEx (zero-shot top-10) 76.4 Zero-Shot Information Extraction as a Unified Text-to-Triple Translation cgraywang/deepex 2021
18 DeepStruct multi-task w/ finetune 76.8 DeepStruct: Pretraining of Language Models for Structure Prediction cgraywang/deepstruct 2022
19 Deepstruct zero-shot 36.1 DeepStruct: Pretraining of Language Models for Structure Prediction cgraywang/deepstruct 2022
20 DeepEx (zero-shot top-1) 49.2 Zero-Shot Information Extraction as a Unified Text-to-Triple Translation cgraywang/deepex 2021
1–20 / 35 다음 → 페이지당 10 20 50 100