I'm trying to read this paper describing Google's LSTM architecture for machine translation from 2016. However, I'm getting stuck as certain things are described too vaguely for me.
This is a picture of the architecture. I just want to understand the encoder for now (the left block). The pink and green blocks are LSTM cells, I understand.
Are these LSTM cells the same kind that are described on Wikipedia? Because those have two outputs (the "mask" $c_t$ and the state $h_t$) and three inputs. Which arrow is which in the Google diagram?
Where are the recurrent connections going? Does the hidden state of each LSTM cell go into the cell on the right at the next timestep? The cell above? Into itself? All three? What about the mask vector?
What goes where? That is, where do the inputs enter? The text $x_3, x_2, ...$ at the bottom of the encoder block is not clear to me. So the different tokens of the input go into different cells? What if there are more tokens in the sentence than cells?