Non-Autoregressive Machine Translation

AbstractWe propose to train a non-autoregressive machine translation model to minimize the energy defined by a pretrained autoregressive model. In particular, we view our non-autoregressive translation system as an inference …...

AbstractWe propose an efficient inference procedure for non-autoregressive machine translation that iteratively refines translation purely in the continuous space. Given a continuous latent variable model for machine translation (Shu et …...

AbstractLatent alignment objectives such as CTC and AXE significantly improve non-autoregressive machine translation models. Can they improve autoregressive models as well? We explore the possibility of training autoregressive machine translation …...

AbstractNon-autoregressive (NAR) machine translation has recently received significant developments and now achieves comparable quality with autoregressive (AR) models on some benchmarks while providing an efficient alternative to AR inference. However, …...

AbstractNon-autoregressive machine translation (NAT) models have lower translation quality than autoregressive translation (AT) models because NAT decoders do not depend on previous target tokens in the decoder input. We propose …...