A review of the state-of-the-art in automatic post-editing

F Do Carmo, D Shterionov, J Moorkens, J Wagner… - Machine …, 2021 - Springer
This article presents a review of the evolution of automatic post-editing, a term that describes
methods to improve the output of machine translation systems, based on knowledge …

Findings of the 2016 conference on machine translation (wmt16)

O Bojar, R Chatterjee, C Federmann… - First conference on …, 2016 - research.ed.ac.uk
This paper presents the results of the WMT16 shared tasks, which included five machine
translation (MT) tasks (standard news, IT-domain, biomedical, multimodal, pronoun), three …

[PDF][PDF] Findings of the 2014 workshop on statistical machine translation

O Bojar, C Buck, C Federmann, B Haddow… - Proceedings of the …, 2014 - aclanthology.org
This paper presents the results of the WMT14 shared tasks, which included a standard news
translation task, a separate medical translation task, a task for run-time estimation of …

Systran's pure neural machine translation systems

J Crego, J Kim, G Klein, A Rebollo, K Yang… - arxiv preprint arxiv …, 2016 - arxiv.org
Since the first online demonstration of Neural Machine Translation (NMT) by LISA, NMT
development has recently moved from laboratory to production systems as demonstrated by …

Log-linear combinations of monolingual and bilingual neural machine translation models for automatic post-editing

M Junczys-Dowmunt, R Grundkiewicz - arxiv preprint arxiv:1605.04800, 2016 - arxiv.org
This paper describes the submission of the AMU (Adam Mickiewicz University) team to the
Automatic Post-Editing (APE) task of WMT 2016. We explore the application of neural …

ESCAPE: a large-scale synthetic corpus for automatic post-editing

M Negri, M Turchi, R Chatterjee, N Bertoldi - arxiv preprint arxiv …, 2018 - arxiv.org
Training models for the automatic correction of machine-translated text usually relies on data
consisting of (source, MT, human post-edit) triplets providing, for each source sentence …

Can automatic post-editing improve NMT?

S Chollampatt, RH Susanto, L Tan… - arxiv preprint arxiv …, 2020 - arxiv.org
Automatic post-editing (APE) aims to improve machine translations, thereby reducing human
post-editing effort. APE has had notable success when used with statistical machine …

Improving zero-shot translation of low-resource languages

SM Lakew, QF Lotito, M Negri, M Turchi… - arxiv preprint arxiv …, 2018 - arxiv.org
Recent work on multilingual neural machine translation reported competitive performance
with respect to bilingual models and surprisingly good performance even on (zeroshot) …

[PDF][PDF] Exploring the planet of the apes: a comparative study of state-of-the-art methods for mt automatic post-editing

R Chatterjee, M Weller, M Negri… - Proceedings of the 53rd …, 2015 - aclanthology.org
Downstream processing of machine translation (MT) output promises to be a solution to
improve translation quality, especially when the MT system's internal decoding process is …

Multilingual neural machine translation for low-resource languages

SM Lakew, M Federico, M Negri… - IJCoL. Italian Journal …, 2018 - journals.openedition.org
In recent years, Neural Machine Translation (NMT) has been shown to be more effective
than phrase-based statistical methods, thus quickly becoming the state of the art in machine …