Domain Adaptation (DA) of Neural Machine Translation (NMT) model often relies on a pre-trained general NMT model which is adapted to the new domain on a sample of in-domain parallel data.
The former normalizes the input to fix its distribution in terms of the mean and variance, while the latter returns the output to the original distribution.
For example, it is difficult to figure out which models provide state-of-the-art performance, as recently proposed models have often been evaluated with different datasets and experiment environments.
To address this issue, this paper presents a novel meta-learning algorithm for unsupervised neural machine translation (UNMT) that trains the model to adapt to another domain by utilizing only a small amount of training data.
Predicting road traffic speed is a challenging task due to different types of roads, abrupt speed change and spatial dependencies between roads; it requires the modeling of dynamically changing spatial dependencies among roads and temporal patterns over long input sequences.
Attention networks, a deep neural network architecture inspired by humans' attention mechanism, have seen significant success in image captioning, machine translation, and many other applications.