As machine translation (MT) systems progress at a rapid pace, questions of\ntheir adequacy linger. In this study we focus on negation, a universal, core\nproperty of human language that significantly affects the semantics of an\nutterance. We investigate whether translating negation is an issue for modern\nMT systems using 17 translation directions as test bed. Through thorough\nanalysis, we find that indeed the presence of negation can significantly impact\ndownstream quality, in some cases resulting in quality reductions of more than\n60%. We also provide a linguistically motivated analysis that directly explains\nthe majority of our findings. We release our annotations and code to replicate\nour analysis here: https://github.com/mosharafhossain/negation-mt.\n