TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

Models/MT-DNN

MT-DNN

Reported on 10 benchmarks across 4 tasks · 2 papers · 2 SOTA

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

Natural Language Processing11 results

  • Natural Language InferenceonSciTail
    Accuracy· 2019-01-31
    94.1
    best: 96.8 (CA-MTL)
    SOTA
    Multi-Task Deep Neural Networks for Natural Language UnderstandingarXiv:1901.11504
  • Natural Language InferenceonSNLI
    % Test Accuracy· 2019-01-31
    91.6
    best: 94.7 (UnitedSynT5 (3B))
    SOTA
    Multi-Task Deep Neural Networks for Natural Language UnderstandingarXiv:1901.11504
  • Sentiment AnalysisonSST-2 Binary classification
    Accuracy· 2019-11-08
    93.6
    best: 97.5 (T5-11B)
    SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized OptimizationarXiv:1911.03437
  • Natural Language InferenceonSNLI
    % Train Accuracy· 2019-01-31
    97.2
    best: 99.7 (+ Unigram and bigram features)
    Multi-Task Deep Neural Networks for Natural Language UnderstandingarXiv:1901.11504
  • Natural Language InferenceonMultiNLI
    Matched· 2019-01-31
    86.7
    best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
    Multi-Task Deep Neural Networks for Natural Language UnderstandingarXiv:1901.11504
  • Natural Language InferenceonMultiNLI
    Mismatched· 2019-01-31
    86
    best: 92.4 (Turing NLR v5 XXL 5.4B (fine-tuned))
    Multi-Task Deep Neural Networks for Natural Language UnderstandingarXiv:1901.11504
  • Semantic Textual SimilarityonQuora Question Pairs
    Accuracy· 2019-01-31
    89.6
    best: 92.4 (data2vec)
    Multi-Task Deep Neural Networks for Natural Language UnderstandingarXiv:1901.11504
  • Semantic Textual SimilarityonQuora Question Pairs
    F1· 2019-01-31
    72.4
    best: 90.7 (ALICE)
    Multi-Task Deep Neural Networks for Natural Language UnderstandingarXiv:1901.11504
  • Sentiment AnalysisonSST-2 Binary classification
    Accuracy· 2019-01-31
    95.6
    best: 97.5 (T5-11B)
    Multi-Task Deep Neural Networks for Natural Language UnderstandingarXiv:1901.11504
  • Paraphrase IdentificationonQuora Question Pairs
    Accuracy· 2019-01-31
    89.6
    best: 92.4 (data2vec)
    Multi-Task Deep Neural Networks for Natural Language UnderstandingarXiv:1901.11504
  • Paraphrase IdentificationonQuora Question Pairs
    F1· 2019-01-31
    72.4
    best: 90.7 (ALICE)
    Multi-Task Deep Neural Networks for Natural Language UnderstandingarXiv:1901.11504