In this extended abstract, we briefly outline Semantic Probabilistic Layers [1], a new layer that can be plugged into any neural network to guarantee its predictions are consistent with a set of predefined symbolic constraints while being amenable to end-to-end learning via maximum likelihood. SPLs can faithfully, and eficiently, model complex SOP tasks beyond the reach of alternative neuro-symbolic layers. We empirically demonstrate that SPLs outperform these competitors in terms of accuracy on an array of challenging structured-output prediction tasks.