# Can a character-level Seq2Seq setup learn to perfectly reconstruct structured data like name strings?

If not perfect, how well can they do? For example, if I give the Seq2Seq setup a name it did not see in the training process, can it output the same name without error?

Example

name = "Will Smith"
output = DecoderRNN(EncoderRNN(name))
can_this_be_true = name == output