# NMT, What if we do not pass input for decoder?

For transformer-based neural machine translation (NMT), take English-Chinese for example, we pass English for encoder and use decoder input(Chinese) attend to encoder output, then final output.

What if we do not pass input for decoder and consider it as a 'memory' model for translation. Is it possible and what will happen?

It seems decoder could be removed and there only exist encoder.

Could I do translation task like text generation? See:

https://github.com/salesforce/ctrl/blob/master/generation.py

https://einstein.ai/presentations/ctrl.pdf

Nevertheless, if NAR NMT were possible, it would lead to huge speedups ($$O(1)$$ instead of $$O(n)$$ complexity). This is currently a very active line of research. Most of the proposed attempts rely on creating some sort of intermediate (latent) representation to feed to the decoder, which then decodes non-autoregressively.