Salesforce Research: Fully-Parallel Text Generation for Neural Machine Translation

So far all text generation models based on neural networks and deep learning have had the same, surprisingly human, limitation: like us, they can only produce language word by word or even letter by letter. Today Salesforce is announcing a neural machine translation system that can overcome this limitation, producing translations an entire sentence at a time in a fully parallel way. This means up to 10x lower user wait time, with similar translation quality to the best available word-by-word models.

An impressive example of rebuilding an entire algorithm bottom-up to be parallelized. This is a major step forwards in a very hot research area.


Want to receive more content like this in your inbox?