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/HateBERT

HateBERT

Reported on 22 benchmarks across 4 tasks · 2 papers · 6 SOTA

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

Natural Language Processing14 results

  • Abuse DetectiononHatEval
    Macro F1· 2020-10-23
    0.494
    SOTA
    HateBERT: Retraining BERT for Abusive Language Detection in EnglisharXiv:2010.12472
  • Abuse DetectiononAbusEval
    Macro F1· 2020-10-23
    0.742
    SOTA
    HateBERT: Retraining BERT for Abusive Language Detection in EnglisharXiv:2010.12472
  • Abuse DetectiononOffensEval 2019
    Macro F1· 2020-10-23
    0.805
    SOTA
    HateBERT: Retraining BERT for Abusive Language Detection in EnglisharXiv:2010.12472
  • Hate Speech DetectiononHatEval
    Macro F1· 2020-10-23
    0.494
    SOTA
    HateBERT: Retraining BERT for Abusive Language Detection in EnglisharXiv:2010.12472
  • Hate Speech DetectiononAbusEval
    Macro F1· 2020-10-23
    0.742
    SOTA
    HateBERT: Retraining BERT for Abusive Language Detection in EnglisharXiv:2010.12472
  • Hate Speech DetectiononOffensEval 2019
    Macro F1· 2020-10-23
    0.805
    SOTA
    HateBERT: Retraining BERT for Abusive Language Detection in EnglisharXiv:2010.12472
  • Text ClassificationonCivil Comments
    AUROC· 2023-01-26
    0.9791
    best: 0.9818 (RoBERTa Focal Loss)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • Text ClassificationonCivil Comments
    GMB BNSP· 2023-01-26
    0.9589
    best: 0.9644 (DistilBERT)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • Text ClassificationonCivil Comments
    GMB BPSN· 2023-01-26
    0.8915
    best: 0.901 (RoBERTa Focal Loss)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • Text ClassificationonCivil Comments
    GMB Subgroup· 2023-01-26
    0.8744
    best: 0.8807 (RoBERTa Focal Loss)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • Text ClassificationonCivil Comments
    Macro F1· 2023-01-26
    0.3679
    best: 0.4749 (RoBERTa BCE)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • Text ClassificationonCivil Comments
    Micro F1· 2023-01-26
    0.4844
    best: 0.5958 (Unfreeze Glove ResNet 44)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • Text ClassificationonCivil Comments
    Precision· 2023-01-26
    0.3297
    best: 0.4835 (Unfreeze Glove ResNet 44)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • Text ClassificationonCivil Comments
    Recall· 2023-01-26
    0.9165
    best: 0.9254 (XLNet)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125

Methodology8 results

  • ClassificationonCivil Comments
    AUROC· 2023-01-26
    0.9791
    best: 0.9818 (RoBERTa Focal Loss)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • ClassificationonCivil Comments
    GMB BNSP· 2023-01-26
    0.9589
    best: 0.9644 (DistilBERT)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • ClassificationonCivil Comments
    GMB BPSN· 2023-01-26
    0.8915
    best: 0.901 (RoBERTa Focal Loss)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • ClassificationonCivil Comments
    GMB Subgroup· 2023-01-26
    0.8744
    best: 0.8807 (RoBERTa Focal Loss)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • ClassificationonCivil Comments
    Macro F1· 2023-01-26
    0.3679
    best: 0.4749 (RoBERTa BCE)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • ClassificationonCivil Comments
    Micro F1· 2023-01-26
    0.4844
    best: 0.5958 (Unfreeze Glove ResNet 44)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • ClassificationonCivil Comments
    Precision· 2023-01-26
    0.3297
    best: 0.4835 (Unfreeze Glove ResNet 44)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125
  • ClassificationonCivil Comments
    Recall· 2023-01-26
    0.9165
    best: 0.9254 (XLNet)
    A benchmark for toxic comment classification on Civil Comments datasetarXiv:2301.11125