moderation-english-text-classification

Classifies harmful English text

1
Model inference in progress...
Loading Model for the first time may take a few minutes.

Notes

Text Moderation English - BERT-based Model

Link to Training Data

Multilingual text moderation model is observed to have better performance.

Taxonomy:

toxic, severe_toxic, obscene, threat, insult, identity_hate
  • ID
  • Model Type ID
    Text Classifier
  • Input Type
    text
  • Output Type
    concepts
  • Description
    Classifies harmful English text
  • Last Updated
    Jan 06, 2023
  • Privacy
    PUBLIC
  • Use Case
  • Toolkit
  • License
  • Share
  • Badge
    moderation-english-text-classification