Auto-Encoding Variational Neural Machine Translation

Understand

We present a deep generative model of bilingual sentence pairs for machine translation.

• The model generates source and target sentences jointly from a shared latent representation and is parameterised by neural networks.
• We perform efficient training using amortised variational inference and reparameterised gradients.
• Additionally, we discuss the statistical implications of joint modelling and propose an efficient approximation to maximum a posteriori decoding for fast test-time predictions.