A survey on non-autoregressive generation for neural machine translation and beyond
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 …
(NMT) to speed up inference, has attracted much attention in both machine learning and …
Ar-diffusion: Auto-regressive diffusion model for text generation
Diffusion models have gained significant attention in the realm of image generation due to
their exceptional performance. Their success has been recently expanded to text generation …
their exceptional performance. Their success has been recently expanded to text generation …
A survey of non-autoregressive neural machine translation
F Li, J Chen, X Zhang - Electronics, 2023 - mdpi.com
Non-autoregressive neural machine translation (NAMT) has received increasing attention
recently in virtue of its promising acceleration paradigm for fast decoding. However, these …
recently in virtue of its promising acceleration paradigm for fast decoding. However, these …
What Have We Achieved on Non-autoregressive Translation?
Recent advances have made non-autoregressive (NAT) translation comparable to
autoregressive methods (AT). However, their evaluation using BLEU has been shown to …
autoregressive methods (AT). However, their evaluation using BLEU has been shown to …
Improving Non-autoregressive Machine Translation with Error Exposure and Consistency Regularization
X Chen, S Duan, G Liu - arXiv preprint arXiv:2402.09725, 2024 - arxiv.org
Being one of the IR-NAT (Iterative-refinemennt-based NAT) frameworks, the Conditional
Masked Language Model (CMLM) adopts the mask-predict paradigm to re-predict the …
Masked Language Model (CMLM) adopts the mask-predict paradigm to re-predict the …
Non-autoregressive models for fast sequence generation
Autoregressive (AR) models have achieved great success in various sequence generation
tasks. However, AR models can only generate target sequence word-by-word due to the AR …
tasks. However, AR models can only generate target sequence word-by-word due to the AR …
SDPSAT: Syntactic Dependency Parsing Structure-Guided Semi-Autoregressive Machine Translation
X Chen, Y Zhao, J Guo, S Duan, G Liu - International Conference on …, 2023 - Springer
The advent of non-autoregressive machine translation (NAT) accelerates the decoding
superior to autoregressive machine translation (AT) significantly, while bringing about a …
superior to autoregressive machine translation (AT) significantly, while bringing about a …
Enhancing Machine Translation Quality through Progressive Multi-Granularity Training Techniques
E Wong - Integrated Journal of Science and Technology, 2024 - ijstindex.com
Abstract Machine translation (MT) systems have seen significant advancements with the
introduction of neural network models. However, improving translation quality remains a …
introduction of neural network models. However, improving translation quality remains a …