On Adversarial Examples for Character-Level Neural Machine Translation

COLING 2018 Javid EbrahimiDaniel LowdDejing Dou

Evaluating on adversarial examples has become a standard procedure to measure robustness of deep learning models. Due to the difficulty of creating white-box adversarial examples for discrete text input, most analyses of the robustness of NLP models have been done through black-box adversarial examples... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.