infiniterik/desc-detoxify-sicon

Fine-tuned instance of T5-Large for detoxifying discourse surrounding abortion debate. Implementation and ethical considerations are listed in the paper Detoxifying Online Discourse: A Guided Response Generation Approach for Reducing Toxicity in User-Generated Text.

Github repository can be found here.

Citation

BibTeX:

@inproceedings{bose-etal-2023-detoxifying,
    title = "Detoxifying Online Discourse: A Guided Response Generation Approach for Reducing Toxicity in User-Generated Text",
    author = "Bose, Ritwik  and Perera, Ian  and Dorr, Bonnie",
    booktitle = "Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.sicon-1.2",
    pages = "9--14"
}