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/Methodology/Classification/Civil Comments

Classification on Civil Comments

Metric: Macro F1 (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Macro F1▼AugmentationsPaperDate↕Code
1RoBERTa BCE0.4749NoA benchmark for toxic comment classification on ...2023-01-26Code
2RoBERTa Focal Loss0.4648NoA benchmark for toxic comment classification on ...2023-01-26Code
3Unfreeze Glove ResNet 440.4648NoA benchmark for toxic comment classification on ...2023-01-26Code
4Freeze Glove ResNet 440.4189NoA benchmark for toxic comment classification on ...2023-01-26Code
5DistilBERT0.3879NoA benchmark for toxic comment classification on ...2023-01-26Code
6Unfreeze Glove ResNet 560.3778NoA benchmark for toxic comment classification on ...2023-01-26Code
7HateBERT0.3679NoA benchmark for toxic comment classification on ...2023-01-26Code
8BERTweet0.3612NoA benchmark for toxic comment classification on ...2023-01-26Code
9AlBERT0.3541NoA benchmark for toxic comment classification on ...2023-01-26Code
10Compact Convolutional Transformer (CCT)0.3428NoA benchmark for toxic comment classification on ...2023-01-26Code
11XLNet0.3336NoA benchmark for toxic comment classification on ...2023-01-26Code