File:fig11.png

Figure 1: Toy illustration of the principles guiding the design of our objective function. Left (autoencoding): the model is trained to reconstruct a sentence from a noisy version of it. $x$ is the target, $C(x)$ is the noisy input, $\hat{x}$ is the reconstruction. Right (translation): the model is trained to translate a sentence in the other domain. The input is a noisy translation (in this case, from source-to-target) produced by the model itself, $M,$ at the previous iteration $(t), y=M^{(t)}(x) .$ The model is symmetric, and we repeat the same process in the other language. See text for more details.