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 …

Natural language generation (NLG) is an essential component of task-oriented dialog
systems. Despite the recent success of neural approaches for NLG, they are typically …

While many parallel corpora are not publicly accessible for data copyright, data privacy and
competitive differentiation reasons, trained translation models are increasingly available on …

Most data selection research in machine translation focuses on improving a single domain.
We perform data selection for multiple domains at once. This is achieved by carefully …

Domain Adaptation is widely used in practical applications of neural machine translation,
which aims to achieve good performance on both the general-domain and in-domain …

Neural machine translation often adopts the fine-tuning approach to adapt to specific
domains. However, nonrestricted fine-tuning can easily degrade on the general domain and …

In the evolving landscape of Neural Machine Translation (NMT), the pretrain-then-finetune
paradigm has yielded impressive results. However, the persistent challenge of Catastrophic …

Neural machine translation (NMT) models are data-driven and require large-scale training
corpus. In practical applications, NMT models are usually trained on a general domain …