Let’s assume I have “abbcab”-> {“Apple”,”Banana”}, “Bibb”-> {“Carrot”,"Padding"}. where the feature is a sequence of characters, so a string, and the target is a list of words. The target maximum length is 11, and the maximum feature length is 208. While building an RNN, I just set input-> NetEncoder[{"Characters"}], but I want to output-> NetDecoder[{"Tokens", targetVal}]. However, I don't know how to set up the last layer to get such output. I did check the tutorial/NeuralNetworksSequenceLearning##1680168479