99 citations · 245 across the 10 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.CL2019★ 99 cited
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
Di Jin, Zhijing Jin, Joey Tianyi Zhou +1
Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models…
cs.CL2019★ 3 cited
IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation
Zhijing Jin, Di Jin, Jonas Mueller +2
Text attribute transfer aims to automatically rewrite sentences such that they possess certain linguistic attributes, while simultaneously preserving their semantic content. This t…