conftrace_

text perturbation

32 papers

Explore in graph

Co-occurring keywords · papers mentioning both

adversarial attack (17) text classification (8) natural language processing (5) language model (4) masked language model (4) model robustness (4) large language model (3) adversarial training (3) data augmentation (3) adversarial sample (2)

Papers

MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation ACL 2021 Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models ACL 2021 Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations EMNLP 2021 A Differentially Private Text Perturbation Method Using Regularized Mahalanobis Metric EMNLP 2020 BERT-ATTACK: Adversarial Attack Against BERT Using BERT EMNLP 2020 Large Scale Author Obfuscation Using Siamese Variational Auto-Encoder: The SiamAO System COLING 2020 Generating Fluent Adversarial Examples for Natural Languages ACL 2019