3 projects are covered by this repo:

The first two involve T5 and other models for automatic hate speech detection and the 3rd one is T5 for Patronizing and Condescending Language (PCL) Detection - SemEval-2022 Task 4

License:

All codes and models are released under CC-BY 4.0.

Contact:

Feel free to contact us for further enquiry.

How do I cite?

Please, cite any of these relevant papers if you use the code.

@INPROCEEDINGS{9892696,
  author={Sabry, Sana Sabah and Adewumi, Tosin and Abid, Nosheen and Kovács, György and Liwicki, Foteini and Liwicki, Marcus},
  booktitle={2022 International Joint Conference on Neural Networks (IJCNN)}, 
  title={HaT5: Hate Language Identification using Text-to-Text Transfer Transformer}, 
  year={2022},
  volume={},
  number={},
  pages={1-7},
  doi={10.1109/IJCNN55064.2022.9892696}}

@article{adewumi2022t5,
  title={T5 for Hate Speech, Augmented Data and Ensemble},
  author={Adewumi, Tosin and Sabry, Sana Sabah and Abid, Nosheen and Liwicki, Foteini and Liwicki, Marcus},
  journal={arXiv preprint arXiv:2210.05480},
  year={2022}
}

@article{adewumi2022ml_ltu,
  title={ML\_LTU at SemEval-2022 Task 4: T5 Towards Identifying Patronizing and Condescending Language},
  author={Adewumi, Tosin and Alkhaled, Lama and Alkhaled, Hamam and Liwicki, Foteini and Liwicki, Marcus},
  journal={arXiv preprint arXiv:2204.07432},
  year={2022}
}