Non-autoregressive (NAR) generation, which is first proposed in neural machine translation
(NMT) to speed up inference, has attracted much attention in both machine learning and …

Recent work on non-autoregressive neural machine translation (NAT) aims at improving the
efficiency by parallel decoding without sacrificing the quality. However, existing NAT …

Fully non-autoregressive neural machine translation (NAT) is proposed to simultaneously
predict tokens with single forward of neural networks, which significantly reduces the …

This paper presents two strong methods, CTC and Imputer, for non-autoregressive machine
translation that model latent alignments with dynamic programming. We revisit CTC for …

We propose a new training objective named order-agnostic cross entropy (OaXE) for fully
non-autoregressive translation (NAT) models. OaXE improves the standard cross-entropy …

Non-autoregressive neural machine translation (NAMT) has received increasing attention
recently in virtue of its promising acceleration paradigm for fast decoding. However, these …

Non-autoregressive neural machine translation (NAT) generates each target word in parallel
and has achieved promising inference acceleration. However, existing NAT models still …

Non-autoregressive neural machine translation (NART) models suffer from the multi-
modality problem which causes translation inconsistency such as token repetition. Most …

Recent years have witnessed an increasing use of coordinated accounts on social media,
operated by misinformation campaigns to influence public opinion and manipulate social …

Non-autoregressive Transformer (NAT) is a family of text generation models, which aims to
reduce the decoding latency by predicting the whole sentences in parallel. However, such …