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/XLNet (single model)

XLNet (single model)

Reported on 11 benchmarks across 4 tasks · 1 paper · 11 SOTA

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

Natural Language Processing15 results

  • Question AnsweringonSQuAD1.1 dev
    EM· uses extra data· 2019-06-19
    89.7
    best: 90.06 (T5-11B)
    SOTA
    XLNet: Generalized Autoregressive Pretraining for Language UnderstandingarXiv:1906.08237
  • Question AnsweringonSQuAD1.1 dev
    F1· uses extra data· 2019-06-19
    95.1
    best: 95.77 (XLNet+DSC)
    SOTA
    XLNet: Generalized Autoregressive Pretraining for Language UnderstandingarXiv:1906.08237
  • Question AnsweringonSQuAD1.1
    EM· 2019-06-19
    89.898
    best: 90.622 ({ANNA} (single model))
    SOTA
    XLNet: Generalized Autoregressive Pretraining for Language UnderstandingarXiv:1906.08237
  • Question AnsweringonSQuAD1.1
    F1· 2019-06-19
    95.08
    best: 95.719 ({ANNA} (single model))
    SOTA
    XLNet: Generalized Autoregressive Pretraining for Language UnderstandingarXiv:1906.08237
  • Question AnsweringonSQuAD2.0 dev
    EM· 2019-06-19
    87.9
    SOTA
    XLNet: Generalized Autoregressive Pretraining for Language UnderstandingarXiv:1906.08237
  • Question AnsweringonSQuAD2.0 dev
    F1· 2019-06-19
    90.6
    SOTA
    XLNet: Generalized Autoregressive Pretraining for Language UnderstandingarXiv:1906.08237
  • Question AnsweringonSQuAD2.0
    EM· 2019-06-19
    87.926
    best: 90.939 (IE-Net (ensemble))
    SOTA
    XLNet: Generalized Autoregressive Pretraining for Language UnderstandingarXiv:1906.08237
  • Question AnsweringonSQuAD2.0
    F1· 2019-06-19
    90.689
    best: 93.214 (IE-Net (ensemble))
    SOTA
    XLNet: Generalized Autoregressive Pretraining for Language UnderstandingarXiv:1906.08237
  • Natural Language InferenceonMultiNLI
    Matched· 2019-06-19
    90.8
    best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
    SOTA
    XLNet: Generalized Autoregressive Pretraining for Language UnderstandingarXiv:1906.08237
  • Semantic Textual SimilarityonSTS Benchmark
    Pearson Correlation· 2019-06-19
    0.925
    best: 0.929 (MT-DNN-SMART)
    SOTA
    XLNet: Generalized Autoregressive Pretraining for Language UnderstandingarXiv:1906.08237
  • Sentiment AnalysisonSST-2 Binary classification
    Accuracy· 2019-06-19
    97
    best: 97.5 (T5-11B)
    SOTA
    XLNet: Generalized Autoregressive Pretraining for Language UnderstandingarXiv:1906.08237
  • Question AnsweringonSQuAD1.1
    EM· uses extra data· 2019-06-19
    89.898
    best: 90.622 ({ANNA} (single model))
    XLNet: Generalized Autoregressive Pretraining for Language UnderstandingarXiv:1906.08237
  • Question AnsweringonSQuAD1.1
    F1· uses extra data· 2019-06-19
    95.08
    best: 95.719 ({ANNA} (single model))
    XLNet: Generalized Autoregressive Pretraining for Language UnderstandingarXiv:1906.08237
  • Question AnsweringonSQuAD2.0
    EM
    86.346
    best: 90.939 (IE-Net (ensemble))
  • Question AnsweringonSQuAD2.0
    F1
    89.133
    best: 93.214 (IE-Net (ensemble))