Decoder from seq2seq for Generative Adversarial Networks

I am currently researching on free text generation using Generative Adversarial Networks. Before somebody tells me that GANs doesn't work well with discrete data (at least when they are trained with gradient descent), it's true, and I know:D, still I am getting some results and I would like to continue this study line:D. I am struggling a little bit with architecture of the generator. I am using TensorFlow for this purpose. My generator consists of a decoder network (the last part of a seq2seq), like the one in the image below.