Despite the strong performance of current NLP models, they can be brittl...
Despite impressive performance in many benchmark datasets, AI models can...
Learning from rationales seeks to augment model training with human-prov...
Two main approaches for evaluating the quality of machine-generated
rati...
Text simplification is concerned with reducing the language complexity a...
Machine learning models are increasingly integrated into societally crit...
Recent advances in deep learning have resulted in a resurgence in the
po...
We introduce an adversarial method for producing high-recall explanation...