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/heuristic majority

heuristic majority

Reported on 12 benchmarks across 5 tasks · 1 paper

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

Natural Language Processing12 results

  • Reading ComprehensiononMuSeRC
    Average F1· 2021-05-03
    0.671
    best: 0.941 (Golden Transformer)
    Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE TasksarXiv:2105.01192
  • Reading ComprehensiononMuSeRC
    EM · 2021-05-03
    0.237
    best: 0.819 (Golden Transformer)
    Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE TasksarXiv:2105.01192
  • Question AnsweringonDaNetQA
    Accuracy· 2021-05-03
    0.642
    best: 0.917 (Golden Transformer)
    Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE TasksarXiv:2105.01192
  • Common Sense ReasoningonRWSD
    Accuracy· 2021-05-03
    0.669
    best: 0.84 (Human Benchmark)
    Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE TasksarXiv:2105.01192
  • Common Sense ReasoningonPARus
    Accuracy· 2021-05-03
    0.478
    best: 0.982 (Human Benchmark)
    Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE TasksarXiv:2105.01192
  • Common Sense ReasoningonRuCoS
    Average F1· 2021-05-03
    0.26
    best: 0.93 (Human Benchmark)
    Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE TasksarXiv:2105.01192
  • Common Sense ReasoningonRuCoS
    EM · 2021-05-03
    0.257
    best: 0.924 (Golden Transformer)
    Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE TasksarXiv:2105.01192
  • Word Sense DisambiguationonRUSSE
    Accuracy· 2021-05-03
    0.595
    best: 0.805 (Human Benchmark)
    Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE TasksarXiv:2105.01192
  • Natural Language InferenceonRCB
    Accuracy· 2021-05-03
    0.438
    best: 0.702 (Human Benchmark)
    Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE TasksarXiv:2105.01192
  • Natural Language InferenceonRCB
    Average F1· 2021-05-03
    0.4
    best: 0.68 (Human Benchmark)
    Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE TasksarXiv:2105.01192
  • Natural Language InferenceonLiDiRus
    MCC· 2021-05-03
    0.147
    best: 0.626 (Human Benchmark)
    Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE TasksarXiv:2105.01192
  • Natural Language InferenceonTERRa
    Accuracy· 2021-05-03
    0.549
    best: 0.92 (Human Benchmark)
    Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE TasksarXiv:2105.01192