The field of machine translation (MT), the automatic translation of written text from one
natural language into another, has experienced a major paradigm shift in recent years …

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

Training data for NLP tasks often exhibits gender bias in that fewer sentences refer to
women than to men. In Neural Machine Translation (NMT) gender bias has been shown to …

Most neural machine translation models only rely on pairs of parallel sentences, assuming
syntactic information is automatically learned by an attention mechanism. In this work, we …

Deep neural networks (DNNs) are becoming a key enabling technique for many application
domains. However, on-device inference on battery-powered, resource-constrained …

Most neural machine translation (NMT) models only rely on parallel sentence pairs, while
the performance drops sharply in low-resource cases, as the models fail to mine the …

For automatic speech translation (AST), end-to-end approaches are outperformed by
cascaded models that transcribe with automatic speech recognition (ASR), then translate …

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

We present Neural Machine Translation (NMT) training using document-level metrics with
batch-level documents. Previous sequence-objective approaches to NMT training focus …

Grammatical error correction (GEC) is one of the areas in natural language processing in
which purely neural models have not yet superseded more traditional symbolic models …