Cat2Vec implementation X = categorical and y = categorical

I am trying to convert categorical values (zipcodes) with Cat2Vec into a matrix which can be used as an input shape for categorical prediction of a target with binary values.

After reading several articles, among which: https://www.yanxishe.com/TextTranslation/1656?from=csdn

I am having trouble to understand two things:

1) With respect to which y in Cat2Vec encoding are you creating embeddings. Is it with respect to the actual target in the dataset you are trying to predict, or can you randomly choose any y column as target? What would be wise?

2) With respect to the y target, if it should be the actual target you are trying to predict with the model. In my case I am trying to predict a binary target (0/1). Would this still work? As the dimensionality of the target is very limited.

Thank you for helping me!