We present a survey covering the state of the art in low-resource machine translation (MT)
research. There are currently around 7,000 languages spoken in the world and almost all …

This paper presents the results of the news translation task, the multilingual low-resource
translation for Indo-European languages, the triangular translation task, and the automatic …

We present the findings of the WMT2022Shared Tasks in Unsupervised MT and VeryLow
Resource Supervised MT with experiments on the language pairs German to/fromUpper …

This paper describes the submissions of Huawei translation services center (HW-TSC) to the
WMT22 Very Low Resource Supervised MT task. We participate in all 6 supervised tracks …

We study the role of an essential hyper-parameter that governs the training of Transformers
for neural machine translation in a low-resource setting: the batch size. Using theoretical …

Résumé We explore the roles and interactions of the hyper-parameters governing
regularization, and propose a range of values applicable to low-resource neural machine …

Machine Translation has made impressive progress in recent years offering close to human-
level performance on many languages, but studies have primarily focused on high-resource …

This paper presents our submissions to WMT 22 shared task in the Unsupervised and Very
Low Resource Supervised Machine Translation tasks. The task revolves around translating …

The cornerstone of multilingual neural translation is shared representations across
languages. Given the theoretically infinite representation power of neural networks …

Low-resource machine translation research often requires building baselines to benchmark
estimates of progress in translation quality. Neural and statistical phrase-based systems are …