Findings of the 2017 conference on machine translation (wmt17)

O Bojar, R Chatterjee, C Federmann, Y Graham… - 2017 - doras.dcu.ie
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 …

Tagged back-translation

I Caswell, C Chelba, D Grangier - arXiv preprint arXiv:1906.06442, 2019 - arxiv.org
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 …

Back-translation sampling by targeting difficult words in neural machine translation

M Fadaee, C Monz - arXiv preprint arXiv:1808.09006, 2018 - arxiv.org
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 …

Evaluating the morphological competence of machine translation systems

F Burlot, F Yvon - 2nd Conference on Machine Translation (WMT17), 2017 - hal.science
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 …

[PDF][PDF] Nmtpy: A flexible toolkit for advanced neural machine translation systems

O Caglayan, M García-Martínez… - The Prague Bulletin …, 2017 - archive.sciendo.com
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 …

From bilingual to multilingual neural‐based machine translation by incremental training

C Escolano, MR Costa‐Jussà… - Journal of the …, 2021 - Wiley Online Library
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 …

GEval: Tool for debugging NLP datasets and models

F Gralinski, A Wróblewska, T Stanisławek… - Proceedings of the …, 2019 - aclanthology.org
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 …

Dual reconstruction: a unifying objective for semi-supervised neural machine translation

W Xu, X Niu, M Carpuat - arXiv preprint arXiv:2010.03412, 2020 - arxiv.org
While Iterative Back-Translation and Dual Learning effectively incorporate monolingual
training data in neural machine translation, they use different objectives and heuristic …

Addressing data sparsity for neural machine translation between morphologically rich languages

M García-Martínez, W Aransa, F Bougares… - Machine …, 2020 - Springer
Translating between morphologically rich languages is still challenging for current machine
translation systems. In this paper, we experiment with various neural machine translation …

Multimodal machine translation

O Caglayan - 2019 - theses.hal.science
Machine translation aims at automatically translating documents from one language to
another without human intervention. With the advent of deep neural networks (DNN), neural …