[P] What are adversarial examples in NLP?

You might be familiar with the idea of adversarial examples in computer vision. My group has been researching adversarial examples in NLP for some time and recently developed TextAttack, a library for generating adversarial examples in NLP. The library is coming along quite well, but I've been facing the same question from people over and over: What are adversarial examples in NLP? Even people with extensive experience with adversarial examples in computer vision have a hard time understanding, at first glance, what types of adversarial examples exist for NLP. We wrote an article to try and answer this question, unpack some jargon, and introduce people to the idea of robustness in NLP models.