NLP has achieved great progress in the past decade through the use of neural models and
large labeled datasets. The dependence on abundant data prevents NLP models from being …

The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …

Data augmentation is an effective way to improve the generalization of deep learning
models. However, the underlying augmentation methods mainly rely on handcrafted …

Although stance detection has made great progress in the past few years, it is still facing the
problem of unseen targets. In this study, we investigate the domain difference between …

Recent years have seen a growing number of publications that analyse Natural Language
Understanding (NLU) datasets for superficial cues, whether they undermine the complexity …

Prior work has uncovered a set of common problems in state-of-the-art context-based
question answering (QA) systems: a lack of attention to the context when the latter conflicts …

We present GradMask, a simple adversarial example detection scheme for natural language
processing (NLP) models. It uses gradient signals to detect adversarially perturbed tokens in …

The monumental achievements of deep learning (DL) systems seem to guarantee the
absolute superiority and robustness of modern DL systems, but they have shown significant …

Recent approaches have exploited weaknesses in monolingual question answering (QA)
models by adding adversarial statements to the passage. These attacks caused a reduction …

With a rise in false, inaccurate, and misleading information in propaganda, news, and social
media, real-world Question Answering (QA) systems face the challenges of synthesizing and …