Donghong Sun

model robustness (2) natural language processing (1) text classification (1) curriculum learning (1) data augmentation (1) text readability (1) adversarial attack (1) black-box attack (1) adversarial defense (1) language model (1) language model robustness (1) perturbation method (1) adversarial text (1) bert fine-tuning (1) encoder-decoder model (1) text perturbation (1) chinese language (1) chinese text (1) text robustness (1) word-level attack (1)