Detecting adversarial samples that are carefully crafted to fool the mod...
Adversarial training is one of the best-performing methods in improving ...
Dataset bias, i.e., the over-reliance on dataset-specific literal heuris...
Dataset bias has attracted increasing attention recently for its detrime...
NER model has achieved promising performance on standard NER benchmarks....
Natural language understanding (NLU) models tend to rely on spurious
cor...
Due to its open-source nature, Android operating system has been the mai...