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/T5-3B

T5-3B

Reported on 23 benchmarks across 10 tasks · 3 papers · 9 SOTA

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

Natural Language Processing18 results

Data-to-Text GenerationonToTTo
BLEU· 2020-05-21
49.5
SOTA
Text-to-Text Pre-Training for Data-to-Text Tasks arXiv:2005.10433
Data-to-Text GenerationonToTTo
PARENT· 2020-05-21
58.4
SOTA
Text-to-Text Pre-Training for Data-to-Text Tasks arXiv:2005.10433
Reading ComprehensiononPhotoChat
F1· 2019-10-23
58.9
best: 63.8 (PaCE)
SOTA
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Reading ComprehensiononPhotoChat
Recall· 2019-10-23
64.6
best: 68 (PaCE)
SOTA
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Semantic Textual SimilarityonMRPC
F1· 2019-10-23
92.5
SOTA
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Semantic ParsingonSPIDER
Exact Match Accuracy (in Dev)· 2021-09-10
71.5
best: 75.5 (T5-3B+PICARD)
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models arXiv:2109.05093
Semantic ParsingonSPIDER
Execution Accuracy (in Dev)· 2021-09-10
74.4
best: 80.5 (RASAT+PICARD)
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models arXiv:2109.05093
Text-To-SQLonSPIDER
Exact Match Accuracy (in Dev)· 2021-09-10
71.5
best: 75.5 (T5-3B+PICARD)
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models arXiv:2109.05093
Text-To-SQLonSPIDER
Execution Accuracy (in Dev)· 2021-09-10
74.4
best: 80.5 (RASAT+PICARD)
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models arXiv:2109.05093
Reading ComprehensiononPhotoChat
Precision· 2019-10-23
54.1
best: 63.3 (PaCE)
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Question AnsweringonSQuAD1.1 dev
EM· uses extra data· 2019-10-23
88.53
best: 90.06 (T5-11B)
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Question AnsweringonSQuAD1.1 dev
F1· uses extra data· 2019-10-23
94.95
best: 95.77 (XLNet+DSC)
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Natural Language InferenceonMultiNLI
Matched· 2019-10-23
91.4
best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Natural Language InferenceonMultiNLI
Mismatched· 2019-10-23
91.2
best: 92.4 (Turing NLR v5 XXL 5.4B (fine-tuned))
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Semantic Textual SimilarityonSTS Benchmark
Pearson Correlation· 2019-10-23
0.906
best: 0.929 (MT-DNN-SMART)
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Semantic Textual SimilarityonSTS Benchmark
Spearman Correlation· 2019-10-23
0.898
best: 0.931 (Mnet-Sim)
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Sentiment AnalysisonSST-2 Binary classification
Accuracy· 2019-10-23
97.4
best: 97.5 (T5-11B)
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Question AnsweringonCronQuestions
Hits@1
25.2
best: 97.8 (GenTKGQA)

Miscellaneous3 results

Intent RecognitiononPhotoChat
F1· 2019-10-23
58.9
best: 63.8 (PaCE)
SOTA
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Intent RecognitiononPhotoChat
Recall· 2019-10-23
64.6
best: 68 (PaCE)
SOTA
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Intent RecognitiononPhotoChat
Precision· 2019-10-23
54.1
best: 63.3 (PaCE)
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683

Adversarial2 results

Text GenerationonToTTo
BLEU· 2020-05-21
49.5
SOTA
Text-to-Text Pre-Training for Data-to-Text Tasks arXiv:2005.10433
Text GenerationonToTTo
PARENT· 2020-05-21
58.4
SOTA
Text-to-Text Pre-Training for Data-to-Text Tasks arXiv:2005.10433