Nested Classification in Tensorflow

I am working on a text classification problem that has an output structure that one could consider nested in the sense that similar child labels fall under the umbrella of parent labels, which are quite different. I am trying to wrap my head around a deep learning architecture that could exploit this structure to enhance predictive performance.

Currently, my Tensorflow model is fairly straightforward:

Input - Fine Tuned BERT - Dense layer - Output

with results being currently acceptable. However, I am thinking that a model that is something like

Input - Fine Tuned BERT - Dense layer - Parent Label - Dense Layer - Child Layer (with outputs nested under their respective parent labels)

would further exploit the structure in these data and enhance predictive performance, especially with regard to misclassifications under the same parent label.

Does this type of approach have a name? Can anyone provide some guidance on how this could be accomplished with the functional API in Tensorflow?