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.

SotA/Natural Language Processing/Text Classification/Civil Comments

Text Classification on Civil Comments

Metric: GMB Subgroup (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕GMB Subgroup▼Extra DataPaperDate↕Code
1RoBERTa Focal Loss0.8807NoA benchmark for toxic comment classification on ...2023-01-26Code
2RoBERTa BCE0.88NoA benchmark for toxic comment classification on ...2023-01-26Code
3BERTweet0.878NoA benchmark for toxic comment classification on ...2023-01-26Code
4DistilBERT0.8762NoA benchmark for toxic comment classification on ...2023-01-26Code
5HateBERT0.8744NoA benchmark for toxic comment classification on ...2023-01-26Code
6AlBERT0.8734NoA benchmark for toxic comment classification on ...2023-01-26Code
7XLNet0.8689NoA benchmark for toxic comment classification on ...2023-01-26Code
8BiLSTM0.8636NoA benchmark for toxic comment classification on ...2023-01-26Code
9Unfreeze Glove ResNet 560.8487NoA benchmark for toxic comment classification on ...2023-01-26Code
10Unfreeze Glove ResNet 440.8421NoA benchmark for toxic comment classification on ...2023-01-26Code
11Freeze Glove ResNet 440.8219NoA benchmark for toxic comment classification on ...2023-01-26Code
12Compact Convolutional Transformer (CCT)0.8133NoA benchmark for toxic comment classification on ...2023-01-26Code