Hierarchical Adversarial Correction to Mitigate Identity Term Bias in Toxicity Detection

Hierarchical Adversarial Correction to Mitigate Identity Term Bias in Toxicity Detection Johannes Schäfer author Ulrich Heid author Roman Klinger author 2024-08 text Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis Orphée De Clercq editor Valentin Barriere editor Jeremy Barnes editor Roman Klinger editor João Sedoc editor Shabnam Tafreshi editor Association for Computational Linguistics Bangkok, Thailand conference publication schafer-etal-2024-hierarchical 10.18653/v1/2024.wassa-1.4 https://aclanthology.org/2024.wassa-1.4/ 2024-08 35 51