While machine translation has traditionally relied on large amounts of parallel corpora, a
recent research line has managed to train both Neural Machine Translation (NMT) and …

In recent years, neural network-based machine translation (MT) approaches have steadily
superseded the statistical MT (SMT) methods, and represents the current state-of-the-art in …

Neural approaches have achieved state-of-the-art accuracy on machine translation but
suffer from the high cost of collecting large scale parallel data. Thus, a lot of research has …

We review motivations, definition, approaches, and methodology for unsupervised cross-
lingual learning and call for a more rigorous position in each of them. An existing rationale …

Pre-training has proven to be effective in unsupervised machine translation due to its ability
to model deep context information in cross-lingual scenarios. However, the cross-lingual …

This paper proposes a novel multilingual multistage fine-tuning approach for low-resource
neural machine translation (NMT), taking a challenging Japanese--Russian pair for …

Unsupervised bilingual word embedding (UBWE), together with other technologies such as
back-translation and denoising, has helped unsupervised neural machine translation …

Availability of bitext dataset has been a key challenge in the conventional machine
translation system which requires surplus amount of parallel data. In this work, we devise an …

Unsupervised cross-lingual language representation initialization methods such as
unsupervised bilingual word embedding (UBWE) pre-training and cross-lingual masked …

This paper presents the NICT's participation in the WMT19 unsupervised news translation
task. We participated in the unsupervised translation direction: German-Czech. Our primary …