Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/ERNIE

ERNIE

Reported on 23 benchmarks across 11 tasks · 3 papers · 14 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing23 results

Relation ExtractiononFewRel
F1· 2019-05-17
88.32
best: 92.9 (DeepEx (zero-shot top-10))
SOTA
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Relation ExtractiononFewRel
Precision· 2019-05-17
88.49
SOTA
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Relation ExtractiononFewRel
Recall· 2019-05-17
88.44
SOTA
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Relation ClassificationonTACRED
F1· 2019-05-17
68
best: 76.8 (DeepStruct multi-task w/ finetune)
SOTA
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Semantic Textual SimilarityonSTS Benchmark
Pearson Correlation· 2019-05-17
0.832
best: 0.929 (MT-DNN-SMART)
SOTA
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Entity LinkingonFIGER
Accuracy· 2019-05-17
57.19
SOTA
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Entity LinkingonFIGER
Macro F1· 2019-05-17
76.51
SOTA
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Entity LinkingonFIGER
Micro F1· 2019-05-17
73.39
SOTA
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Entity Typingon Open Entity
F1· 2019-05-17
75.56
best: 77.6916 (K-Adapter ( fac-adapter ))
SOTA
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Entity Typingon Open Entity
Precision· 2019-05-17
78.42
best: 79.6712 (K-Adapter ( fac-adapter ))
SOTA
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Entity Typingon Open Entity
Recall· 2019-05-17
72.9
best: 76.2774 (K-Adapter ( fac-adapter + lin-adapter ))
SOTA
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Natural Language InferenceonXNLI Chinese Dev
Accuracy· 2019-04-19
79.9
best: 82.6 (ERNIE 2.0 Large)
SOTA
ERNIE: Enhanced Representation through Knowledge Integration arXiv:1904.09223
Natural Language InferenceonXNLI Chinese
Accuracy· 2019-04-19
78.4
best: 81 (ERNIE 2.0 Large)
SOTA
ERNIE: Enhanced Representation through Knowledge Integration arXiv:1904.09223
Named Entity Recognition (NER)onMSRA Dev
F1· 2019-04-19
95
best: 96.3 (ERNIE 2.0 Large)
SOTA
ERNIE: Enhanced Representation through Knowledge Integration arXiv:1904.09223
Text ClassificationonUK Key Stage Readability
F1· 2024-11-26
73.6
best: 99.6 (ELECTRA + ANN)
What Differentiates Educational Literature? A Multimodal Fusion Approach of Transformers and Computational Linguistics arXiv:2411.17593
Relation ExtractiononTACRED
F1· 2019-05-17
67.97
best: 86.6 (RAG4RE)
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Relation ExtractiononTACRED
F1· 2019-05-17
68
best: 86.6 (RAG4RE)
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Natural Language InferenceonMultiNLI
Matched· 2019-05-17
84
best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Natural Language InferenceonMultiNLI
Mismatched· 2019-05-17
83.2
best: 92.4 (Turing NLR v5 XXL 5.4B (fine-tuned))
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Semantic Textual SimilarityonQuora Question Pairs
F1· 2019-05-17
71.2
best: 90.7 (ALICE)
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Sentiment AnalysisonSST-2 Binary classification
Accuracy· 2019-05-17
93.5
best: 97.5 (T5-11B)
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Paraphrase IdentificationonQuora Question Pairs
F1· 2019-05-17
71.2
best: 90.7 (ALICE)
ERNIE: Enhanced Language Representation with Informative Entities arXiv:1905.07129
Named Entity Recognition (NER)onMSRA
F1· 2019-04-19
93.8
best: 96.72 (BERT-MRC+DSC)
ERNIE: Enhanced Representation through Knowledge Integration arXiv:1904.09223

Methodology1 result

ClassificationonUK Key Stage Readability
F1· 2024-11-26
73.6
best: 99.6 (ELECTRA + ANN)
What Differentiates Educational Literature? A Multimodal Fusion Approach of Transformers and Computational Linguistics arXiv:2411.17593