En Large

🚀 MUDES - {Mu}ltilingual {De}tection of Offensive {S}pans

We offer state - of - the - art models for detecting toxic spans in social media texts, bringing value to text safety.

🚀 Quick Start

We provide state-of-the-art models to detect toxic spans in social media texts. We introduce our framework in this paper. We have evaluated our models on Toxic Spans task at SemEval 2021 (Task 5). Our participation in the task is detailed in this paper.

📦 Installation

You can use this model when you have MUDES installed:

pip install mudes

💻 Usage Examples

Basic Usage

from mudes.app.mudes_app import MUDESApp

app = MUDESApp("en-large", use_cuda=False)
print(app.predict_toxic_spans("You motherfucking cunt", spans=True))

📚 Documentation

An experimental demonstration interface called MUDES-UI has been released on GitHub and can be checked out in here.

📄 License

This project is under the apache-2.0 license.

📚 Citing & Authors

If you find this model helpful, feel free to cite our publications

@inproceedings{ranasinghemudes,
 title={{MUDES: Multilingual Detection of Offensive Spans}}, 
 author={Tharindu Ranasinghe and Marcos Zampieri},  
 booktitle={Proceedings of NAACL},
 year={2021}
}

@inproceedings{ranasinghe2021semeval,
  title={{WLV-RIT at SemEval-2021 Task 5: A Neural Transformer Framework for Detecting Toxic Spans}},
  author = {Ranasinghe, Tharindu  and Sarkar, Diptanu and Zampieri, Marcos and Ororbia, Alex},
  booktitle={Proceedings of SemEval},
  year={2021}
}