Non-autoregressive translation (NAT) reduces the decoding latency but su...
Non-autoregressive neural machine translation (NAT) models suffer from t...
Non-autoregressive models achieve significant decoding speedup in neural...
Non-autoregressive translation (NAT) models are typically trained with t...
Non-autoregressive neural machine translation (NAT) suffers from the
mul...
Neural networks tend to gradually forget the previously learned knowledg...
In recent years, Neural Machine Translation (NMT) has achieved notable
r...
Although teacher forcing has become the main training paradigm for neura...
Non-Autoregressive Neural Machine Translation (NAT) has achieved signifi...
Despite the improvement of translation quality, neural machine translati...
Neural machine translation models usually adopt the teacher forcing stra...
Non-Autoregressive Neural Machine Translation (NAT) achieves significant...
Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer ...
Neural machine translation (NMT) models are usually trained with the
wor...