Machine learning (ML) models have been widely applied to various applications, including
image classification, text generation, audio recognition, and graph data analysis. However …

Neural Machine Translation (NMT) has seen tremendous growth in the last ten years since
the early 2000s and has already entered a mature phase. While considered the most widely …

One of the biggest challenges hindering progress in low-resource and multilingual machine
translation is the lack of good evaluation benchmarks. Current evaluation benchmarks either …

Existing work in translation demonstrated the potential of massively multilingual machine
translation by training a single model able to translate between any pair of languages …

We present COMET, a neural framework for training multilingual machine translation
evaluation models which obtains new state-of-the-art levels of correlation with human …

Human evaluation of modern high-quality machine translation systems is a difficult problem,
and there is increasing evidence that inadequate evaluation procedures can lead to …

In this paper, we propose a simple yet effective method to stabilize extremely deep
Transformers. Specifically, we introduce a new normalization function (DeepNorm) to modify …

The quality of human translation was long thought to be unattainable for computer
translation systems. In this study, we present a deep-learning system, CUBBITT, which …

Multi-head self-attention is a key component of the Transformer, a state-of-the-art
architecture for neural machine translation. In this work we evaluate the contribution made …

This paper presents the results of the premier shared task organized alongside the
Conference on Machine Translation (WMT) 2019. Participants were asked to build machine …