Cover not available

Article published In: Translation Spaces
Vol. 13:2 (2024) ► pp.171–199

Get fulltext from our e-platform
JBE logo with link
PDF logo with download linkDownload PDF
EPUB logo with download linkDownload EPUB
authorization required

Is post-editing really faster than human translation?

ORCiD logo with link | University of Manchester
Published online: 19 December 2023
DOI logo with link
https://doi.org/10.1075/ts.22044.ter
Abstract
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.
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 (31)
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.Google Scholar logo with link to Google Scholar
. 2017. BS ISO 18587:2017: Translation Services. Post-Editing of Machine Translation Output. Requirements.Google Scholar logo with link to Google Scholar
Cleff, Thomas. 2014. Exploratory Data Analysis in Business and Economics: An Introduction Using SPSS, Stata, and Excel. Cham: Springer. Google Scholar logo with link to Google Scholar
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. Google Scholar logo with link to Google Scholar
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. Google Scholar logo with link to Google Scholar
IBM. 2021. IBM SPSS Statistics. Accessed November 6, 2021. [URL]
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.Google Scholar logo with link to Google Scholar
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. 2017. Codes for the Representation of Names of Languages. Accessed June 22, 2021. [URL]
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. Google Scholar logo with link to Google Scholar
Mellinger, Christopher D., and Thomas A. Hanson. 2016. Quantitative Research Methods in Translation and Interpreting Studies. Milton Park, Abingdon, Oxon: Routledge. Google Scholar logo with link to Google Scholar
Memsource. 2020. Machine Translation Workshop Series: Kick-off Event Highlights. Accessed April 22, 2022. [URL]
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. Google Scholar logo with link to Google Scholar
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. Google Scholar logo with link to Google Scholar
O’Brien, Sharon. 2011. “Towards Predicting Post-Editing Productivity.” Machine Translation (25): 197–215. Google Scholar logo with link to Google Scholar
PacTranz. 2021. Realistic Translation Times Using Human Translators. Accessed November 16, 2021. [URL]
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. 2022. Project 5: Explore the Data: Normality Tests and Outlier Tests. Accessed July 14, 2023. [URL]
ProZ.com. 2011. Words Revised per Hour. Accessed February 15, 2022. [URL]
ProZ.com. 2016a. How Many Words Can You Proofread per Hour? Accessed February 16, 2022. [URL]
ProZ.com. 2016b. Revision Rate: 2000 Words per Hour – Really? Accessed February 16, 2022. [URL]
ProZ.com. 2018. What Are the Realistic Expectations for Post-Edited Work? Accessed February 16, 2022. [URL]
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. Google Scholar logo with link to Google Scholar
Sánchez-Gijón, Pilar, Joss Moorkens, and Andy Way. 2019. “Post-Editing Neural Machine Translation versus Translation Memory Segments.” Machine Translation, 33 (1): 31–59. Google Scholar logo with link to Google Scholar
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.Google Scholar logo with link to Google Scholar
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. Google Scholar logo with link to Google Scholar
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]
Cited by (2)

Cited by two other publications

Carreira, Oliver
2024. Bad business practices in the language services industry. Translation Spaces 13:2 ► pp. 244 ff. DOI logo
Tieber, Michael & Stefan Baumgarten
2024. Mean machines? Sociotechnical (r)evolution and human labour in the translation and interpreting industry. Perspectives 32:3 ► pp. 379 ff. DOI logo

This list is based on CrossRef data as of 6 december 2025. Please note that it may not be complete. Sources presented here have been supplied by the respective publishers. Any errors therein should be reported to them.

Mobile Menu Logo with link to supplementary files background Layer 1 prag Twitter_Logo_Blue