D

Deoffxlmr Mono Kannada

Developed by Hate-speech-CNERG
This model is used to detect offensive content in Kannada mixed code, fine-tuned based on the XLM-Roberta-Base pre-trained model, and performed excellently in the EACL 2021 shared task.
Downloads 22
Release Time : 3/2/2022

Model Overview

A model specifically designed for offensive content detection in Kannada (pure language and mixed code), trained in a monolingual setting, suitable for social media content moderation.

Model Features

Monolingual optimization
Specifically trained for Kannada (including mixed code), excelling in monolingual scenarios
Shared task winning model
Achieved second place in the Kannada sub-task of the EACL 2021 Dravidian Language Offensive Language Identification Shared Task
Mixed code processing
Capable of effectively handling code-switched content where Kannada is mixed with other languages

Model Capabilities

Text classification
Offensive content detection
Mixed language processing

Use Cases

Content moderation
Social media content filtering
Automatically identifies offensive speech in Kannada social media content
Achieved a weighted F1 score of 0.73 on the test set
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase