Non-Autoregressive Neural Machine Translation

Jiatao GuJames BradburyCaiming XiongVictor O. K. LiRichard Socher

   Papers with code   Abstract  PDF

Existing approaches to neural machine translation condition each output word on previously generated outputs. We introduce a model that avoids this autoregressive property and produces its outputs in parallel, allowing an order of magnitude lower latency during inference... (read more)

Benchmarked Models

No benchmarked models yet. Click here to submit a model.