The development of deep learning techniques has allowed Neural Machine Translation
(NMT) models to become extremely powerful, given sufficient training data and training time …

The principal task in supervised neural machine translation (NMT) is to learn to generate
target sentences conditioned on the source inputs from a set of parallel sentence pairs, and …

Deep encoders have been proven to be effective in improving neural machine translation
(NMT) systems, but training an extremely deep encoder is time consuming. Moreover, why …

Recently, deep models have shown tremendous improvements in neural machine
translation (NMT). However, systems of this kind are computationally expensive and memory …

Residual networks are an Euler discretization of solutions to Ordinary Differential Equations
(ODE). This paper explores a deeper relationship between Transformer and numerical ODE …

Most of the deep neural machine translation (NMT) models are based on a bottom-up
feedforward fashion, in which representations in low layers construct or modulate high …

Transformer structure, stacked by a sequence of encoder and decoder network layers,
achieves significant development in neural machine translation. However, vanilla …

Neural machine translation (NMT) has achieved great success due to the ability to generate
high-quality sentences. Compared with human translations, one of the drawbacks of current …

An end-to-end speech-to-text (S2T) translation model is usually initialized from a pre-trained
speech recognition encoder and a pre-trained text-to-text (T2T) translation decoder …

The Transformer model has achieved state-of-the-art performance in many sequence
modeling tasks. However, how to leverage model capacity with large or variable depths is …