Sparsely activated models (SAMs), such as Mixture-of-Experts (MoE), can
...
Multilingual Neural Machine Translation (NMT) enables one model to serve...
We present META-MT, a meta-learning approach to adapt Neural Machine
Tra...
Modern natural language processing and understanding applications have
e...
Machine translation has made rapid advances in recent years. Millions of...
Spoken Language Translation (SLT) is becoming more widely used and becom...
In this paper, we propose a new universal machine translation approach
f...
In this paper, we introduce a novel approach to generate synthetic data ...