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/BERT-large 340M

BERT-large 340M

Reported on 5 benchmarks across 5 tasks · 4 papers · 3 SOTA

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

Natural Language Processing7 results

  • Natural Language InferenceonWNLI
    Accuracy· 2018-10-11
    65.1
    best: 95.9 (Turing NLR v5 XXL 5.4B (fine-tuned))
    SOTA
    BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingarXiv:1810.04805
  • Natural Language UnderstandingonPDP60
    Accuracy· 2018-10-11
    78.3
    best: 90 (HNN)
    SOTA
    BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingarXiv:1810.04805
  • Word Sense DisambiguationonWords in Context
    Accuracy· 2018-08-28
    65.5
    best: 85.3 (COSINE + Transductive Learning)
    SOTA
    WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning RepresentationsarXiv:1808.09121
  • Coreference ResolutiononWinograd Schema Challenge
    Accuracy· 2021-04-16
    61.4
    best: 100 (PaLM 540B (fine-tuned))
    Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd SchemaarXiv:2104.08161
  • Question AnsweringonCOPA
    Accuracy· 2019-04-22
    80.8
    best: 100 (PaLM 540B (finetuned) )
    SocialIQA: Commonsense Reasoning about Social InteractionsarXiv:1904.09728
  • Coreference ResolutiononWinograd Schema Challenge
    Accuracy· 2019-04-22
    67
    best: 100 (PaLM 540B (fine-tuned))
    SocialIQA: Commonsense Reasoning about Social InteractionsarXiv:1904.09728
  • Coreference ResolutiononWinograd Schema Challenge
    Accuracy· 2018-10-11
    62
    best: 100 (PaLM 540B (fine-tuned))
    BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingarXiv:1810.04805