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 …

Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT).
The community proposed specific network architectures and learning-based methods to …

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

While diffusion models have achieved great success in generating continuous signals such
as images and audio, it remains elusive for diffusion models in learning discrete sequence …

Non-autoregressive translation (NAT) models are typically trained with the cross-entropy
loss, which forces the model outputs to be aligned verbatim with the target sentence and will …

Connectionist Temporal Classification (CTC) is a widely used approach for automatic
speech recognition (ASR) that performs conditionally independent monotonic alignment …

Reinforcement learning (RL) has been widely used in text generation to alleviate the
exposure bias issue or to utilize non-parallel datasets. The reward function plays an …

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 …

Artificial Intelligence (AI) has achieved significant advancements in technology and research
with the development over several decades, and is widely used in many areas including …

Non-autoregressive neural machine translation (NAT) suffers from the multi-modality
problem: the source sentence may have multiple correct translations, but the loss function is …