Gradient-based perturbation of sentence embeddings, followed by a trained decoder, produces adversarial sentences that fool sentiment classifiers and transfer to Amazon Comprehend.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Natural Adversarial Sentence Generation with Gradient-based Perturbation
Gradient-based perturbation of sentence embeddings, followed by a trained decoder, produces adversarial sentences that fool sentiment classifiers and transfer to Amazon Comprehend.