This paper presents the results of the WMT17 shared tasks, which included three machine
translation (MT) tasks (news, biomedical, and multimodal), two evaluation tasks (metrics and …

Recent work in Neural Machine Translation (NMT) has shown significant quality gains from
noised-beam decoding during back-translation, a method to generate synthetic parallel …

Neural Machine Translation has achieved state-of-the-art performance for several language
pairs using a combination of parallel and synthetic data. Synthetic data is often generated by …

While recent changes in Machine Translation state-of-the-art brought translation quality a
step further, it is regularly acknowledged that the standard automatic metrics do not provide …

In this paper, we present nmtpy, a flexible Python toolkit based on Theano for training Neural
Machine Translation and other neural sequence-to-sequence architectures. nmtpy …

A common intermediate language representation in neural machine translation can be used
to extend bilingual systems by incremental training. We propose a new architecture based …

This paper presents a simple but general and effective method to debug the output of
machine learning (ML) supervised models, including neural networks. The algorithm looks …

While Iterative Back-Translation and Dual Learning effectively incorporate monolingual
training data in neural machine translation, they use different objectives and heuristic …

Translating between morphologically rich languages is still challenging for current machine
translation systems. In this paper, we experiment with various neural machine translation …

Machine translation aims at automatically translating documents from one language to
another without human intervention. With the advent of deep neural networks (DNN), neural …