Edinburgh neural machine translation systems for WMT 16
We participated in the WMT 2016 shared news translation task by building neural translation
systems for four language pairs, each trained in both directions: English<-> Czech, English< …
systems for four language pairs, each trained in both directions: English<-> Czech, English< …
Linguistic input features improve neural machine translation
R Sennrich, B Haddow - arXiv preprint arXiv:1606.02892, 2016 - arxiv.org
Neural machine translation has recently achieved impressive results, while using little in the
way of external linguistic information. In this paper we show that the strong learning …
way of external linguistic information. In this paper we show that the strong learning …
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 …
step further, it is regularly acknowledged that the standard automatic metrics do not provide …
Confidence through attention
Attention distributions of the generated translations are a useful bi-product of attention-
based recurrent neural network translation models and can be treated as soft alignments …
based recurrent neural network translation models and can be treated as soft alignments …
[PDF][PDF] Hybrid machine translation by combining output from multiple machine translation systems
M Rikters - Baltic Journal of Modern Computing, 2019 - dspace.lu.lv
This thesis aims to research methods and develop tools that allow to successfully combine
output from various machine translation (MT) systems so that the overall translation quality of …
output from various machine translation (MT) systems so that the overall translation quality of …
Automatic post-editing model for neural machine translation
Techniques are disclosed for training and/or utilizing an automatic post-editing model in
correcting translation error (s) introduced by a neural machine translation model. The …
correcting translation error (s) introduced by a neural machine translation model. The …
[PDF][PDF] The edinburgh/lmu hierarchical machine translation system for wmt 2016
This paper describes the hierarchical phrase-based machine translation system built jointly
by the University of Edinburgh and the University of Munich (LMU) for the shared translation …
by the University of Edinburgh and the University of Munich (LMU) for the shared translation …
[PDF][PDF] The QT21 Combined Machine Translation System for English to Latvian
This paper describes the joint submission of the QT21 projects for the English→ Latvian
translation task of the EMNLP 2017 Second Conference on Machine Translation (WMT …
translation task of the EMNLP 2017 Second Conference on Machine Translation (WMT …
[PDF][PDF] Alignment-based neural networks for machine translation
TAN Alkhouli - 2020 - publications.rwth-aachen.de
After more than a decade of phrase-based systems dominating the scene of machine
translation, neural machine translation has emerged as the new machine translation …
translation, neural machine translation has emerged as the new machine translation …
Error analysis and the role of morphology
M Bollmann, A Søgaard - Proceedings of the 16th Conference of …, 2021 - aclanthology.org
We evaluate two common conjectures in error analysis of NLP models:(i) Morphology is
predictive of errors; and (ii) the importance of morphology increases with the morphological …
predictive of errors; and (ii) the importance of morphology increases with the morphological …