Abstract
Machine Translation (MT) has now become an essential part of the localisation industry. New roles connected with it have emerged, and new technologies have been adopted.
As Language Service Providers (LSPs) need to implement these systems in their workflows – because of client demand, to improve cost efficiency, or to meet the rising demand for translated content – the need for clear guidelines to be followed in the adoption process grows.
In this paper, we describe in detail eight steps to integrate an MT workflow into the translation process. These steps have been identified by analysing existing literature and thoroughly validated through real-world MT implementations by STAR7.
The first step is to identify appropriate use cases. Then we must select the most suitable MT engine. Testing and benchmarking using scoring systems to evaluate the performance of the system is essential, as is supplier engagement in order to involve and inform all stakeholders. As the operational stage begins, several different Post-Editing Machine Translation (PEMT) workflows can be adopted. Quality Assurance (QA) and Language Quality Assessment (LQA) steps can then take place. Finally, feedback from all stakeholders can be collected to improve both the workflow and/or the MT engine performance itself.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alvarez-Vidal, S., Badia, T., Oliver, A.: Implementing MTPE into a real industrial scenario: what do translators need for a fair MT workflow?. In: Fair MT Workflow. MT Summit XVII, Dublin (2019)
Hutchins, J.: Machine translation: a concise history. J. Transl. Stud. 13(1), 29–70 (2010)
ISO 18587:2017. https://www.iso.org/standard/62970.html. Accessed 25 July 2022
Kenny, D., Moorkens, J., do Carmo, F.: Fair MT: Towards ethical, sustainable machine translation. Transl. Spaces 9(1), 1–11 (2020)
Klein, J.: Use MT to simplify and speed up your alignment for TM creation. In: Proceedings of the 14th Conference of The Association for Machine Translation in the Americas, vol. 2: MT User Track, pp. 237–269. https://aclanthology.org/2020.amta-user.pdf. Accessed 05 July 2022
Liu, Q., Zhang, X.: Machine translation general. In: Chan, S. (ed.) The Routledge Encyclopedia of Translation Technology. Routledge, London-New York (2015)
Lommel, A., DePalma, D.: Europe’s Leading Role in Machine Translation. Common Sense Advisory, Cambridge Mass (2016)
Lommel, A.: Augmented Translation: Are We There Yet? https://csa-research.com/Blogs-Events/Blog/augmented-translation-2020. Accessed 25 July 2022
Monti, J.: Dal sogno meccanico alla e-translation: la traduzione automatica è realtà?, Media Duemila – Mensile di Cultura informatica e ICT, 219, 60–67 (2004)
Moorkens, J.: “A tiny cog in a large machine”: Digital Taylorism in the Translation Industry. Transl. Spaces 9(1), 12–34 (2020)
Nimdzi 100 Top LSPs. https://www.nimdzi.com/nimdzi-100-top-lsp/#size-of-the-market-and-projection. Accessed 25 July 2022
Schaier, K.: Can computer translation replace human translation? Hispania 79(1), 96–107 (1996)
Wang, H., Wu, H., He, Z., Huang, L., Ward Church, K.: Progress in Machine Translation, Engineering (2021)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Poeta, N., Giai, E., Turnbull, D. (2022). Optimising the Machine Translation Workflow. In: Ceci, M., Flesca, S., Masciari, E., Manco, G., Raś, Z.W. (eds) Foundations of Intelligent Systems. ISMIS 2022. Lecture Notes in Computer Science(), vol 13515. Springer, Cham. https://doi.org/10.1007/978-3-031-16564-1_44
Download citation
DOI: https://doi.org/10.1007/978-3-031-16564-1_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16563-4
Online ISBN: 978-3-031-16564-1
eBook Packages: Computer ScienceComputer Science (R0)