Article published In:
Translation Spaces: Online-First ArticlesIs post-editing really faster than human translation?
Time efficiency is paramount for the localisation industry, which demands ever-faster turnaround times. However, translation speed is largely underresearched, and there is a lack of clarity about how language service providers (LSPs) can evaluate the performance of their post-editing (PE) and human translation (HT) services. This study constitutes the first large-scale investigation of translation and revision speed in HT and in the PE of neural machine translation, based on real-world data from an LSP. It uses an exploratory data analysis approach to investigate data for 90 million words translated by 879 linguists across 11 language pairs, over 2.5 years. The results of this research indicate that (a) PE is usually but not always faster than HT; (b) average speed values may be misleading; (c) translation speed is highly variable; and (d) edit distance cannot be used as a proxy for post-editing productivity, because it does not correlate strongly with speed.
Keywords: Post-editing, neural machine translation, post-editing speed, post-editing effort, productivity, translation speed, revision, edit distance
Article outline
- 1.Introduction
- 2.Related work
- 3.Data overview and selection
- 4.Exploratory data analysis approach
- 5.Results
- 5.1(A)typical translation speed values
- 5.2Is speed more variable in post-editing or human translation?
- 5.3Correlations between speed and edit distance
- 6.Conclusion
- Acknowledgements
- Notes
-
References
References
Albarino, Seyma
2019 “Reader Polls: Rev Pay Cut, Shift to Hourly Rates, Edit Distance, Translation Regulations.” Slator. Accessed April 22, 2022. [URL]
British Standards Institute
2015 BS EN ISO 17100:2015: Translation Services. Requirements for Translation Services.
2017 BS ISO 18587:2017: Translation Services. Post-Editing of Machine Translation Output. Requirements.
Cleff, Thomas
2014 Exploratory Data Analysis in Business and Economics: An Introduction Using SPSS, Stata, and Excel. Cham: Springer. 
Cumbreño, Cristina, and Nora Aranberri
2021 “What Do You Say? Comparison of Metrics for Post-Editing Effort.” In Explorations in Empirical Translation Process Research. Machine Translation: Technologies and Applications (3), edited by Michael Carl, 57–79. Cham: Springer.
ELIA, EMT, EUATC, FIT Europe, GALA, LIND, and Women in Localization
2022 European Language Industry Survey 2022. Trends, Expectations and Concerns of the European Language Industry. Accessed September 30, 2022. [URL]
Forsyth, David
2018 Probability and Statistics for Computer Science. Cham: Springer.
IBM
Kosmaczewska, Kasia, and Matt Train
2019 “Application of Post-Edited Machine Translation in Fashion eCommerce.” In Proceedings of Machine Translation Summit XVII Volume 2: Translator, Project and User Tracks. Dublin, Ireland, August 19–23, 2019, 167–173. European Association for Machine Translation. Accessed October 2, 2020. [URL]
Krings, Hans P.
2001 Repairing Texts: Empirical Investigations of Machine Translation Post-Editing Processes. Ohio: Kent State University Press.
Läubli, Samuel, Chantal Amrhein, Patrick Düggelin, Beatriz Gonzalez, Alena Zwahlen, and Martin Volk
2019 “Post-Editing Productivity with Neural Machine Translation: An Empirical Assessment of Speed and Quality in the Banking and Finance Domain.” In Proceedings of Machine Translation Summit XVII Volume 1: Research Track. Dublin, Ireland, August 19–23, 2019, 267–272. European Association for Machine Translation. Accessed October 9, 2020. [URL]
Library of Congress
Macken, Lieve, Daniel Prou, and Arda Tezcan
2020 “Quantifying the Effect of Machine Translation in a High-Quality Human Translation Production Process.” Informatics 7 (2): 12.
Mellinger, Christopher D., and Thomas A. Hanson
2016 Quantitative Research Methods in Translation and Interpreting Studies. Milton Park, Abingdon, Oxon: Routledge.
Memsource
Moorkens, Joss, Sharon O’Brien, Igor A. L. da Silva, Norma B. de Lima Fonseca, and Fabio Alves
2015 “Correlations of Perceived Post-Editing Effort with Measurements of Actual Effort.” Machine Translation, 29 (3/4): 267–284.
Moorkens, Joss
2020 “Translation in the Neoliberal Era.” In The Routledge Handbook of Translation and Globalization, edited by Bielsa, Esperança, and Dionysios Kapsaskis, 323–336. London: Routledge.
O’Brien, Sharon
2011 “Towards Predicting Post-Editing Productivity.” Machine Translation (25): 197–215.
PacTranz
Parra Escartín, Carla, and Manuel Arcedillo
2015 “Machine Translation Evaluation Made Fuzzier: A Study on Post-Editing Productivity and Evaluation Metrics in Commercial Settings.” In Proceedings of the MT Summit XV Volume 1: MT Researchers’ Track. Miami, USA, October 30 – November 3, 2015, 131–144. Accessed February 10, 2021. [URL]
Pennsylvania State University
ProZ.com
ProZ.com
ProZ.com
ProZ.com
Rayner, Keith, Timothy J. Slattery, and Nathalie N. Bélanger
2010 “Eye Movements, the Perceptual Span, and Reading Speed.” Psychonomic Bulletin & Review, 17 (6): 834–839.
Sánchez-Gijón, Pilar, Joss Moorkens, and Andy Way
2019 “Post-Editing Neural Machine Translation versus Translation Memory Segments.” Machine Translation, 33 (1): 31–59.
Temizöz, Özlem
2017 “Translator Post-Editing and Subject-Matter Expert Revision versus Subject-Matter Expert Post-Editing and Translator Revision.” Journal of Translator Education and Translation Studies (2) 41: 3–21.
Toral, Antonio, Martijn Wieling, and Andy Way
2018 “Post-editing Effort of a Novel with Statistical and Neural Machine Translation.” Frontiers in Digital Humanities 51: 1–11.
Virino, Virginia
2022 “How Many Words Does a Professional Translator Translate per Day?” Pangeanic. Accessed February 15, 2022. [URL]
Wicklin, Rick
2023 “Weak or strong? How to interpret a Spearman or Kendall correlation.” SAS. Accessed October 5, 2023. [URL]