Zexue He, Bodhisattwa Prasad Majumder, Julian McAuley. Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih, editors, Findings of the Association for Computational Linguistics: EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 16-20 November, 2021. pages 4173-4181, Association for Computational Linguistics, 2021. [doi]
Abstract is missing.