Қарсыласу perturbations

Recent work has proposed several efficient ap- proaches for generating gradient-based adver- sarial perturbations on embeddings and proved that the model’s performance and robustness can be improved when they are …...

AbstractWe often use perturbations to regularize neural models. For neural encoder-decoders, previous studies applied the scheduled sampling (Bengio et al., 2015) and adversarial perturbations (Sato et al., 2019) as perturbations …...