1887
image of Is post-editing really faster than human translation?
USD
Buy:$35.00 + Taxes

Abstract

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.

Loading

Article metrics loading...

/content/journals/10.1075/ts.22044.ter
2023-12-19
2024-10-11
Loading full text...

Full text loading...

References

  1. Albarino, Seyma
    2019 “Reader Polls: Rev Pay Cut, Shift to Hourly Rates, Edit Distance, Translation Regulations.” Slator. AccessedApril 22, 2022. https://slator.com/reader-polls-rev-pay-cut-shift-to-hourly-rates-edit-distance-translation-regulations/
    [Google Scholar]
  2. British Standards Institute
    British Standards Institute 2015BS EN ISO 17100:2015: Translation Services. Requirements for Translation Services.
    [Google Scholar]
  3. British Standards Institute
    British Standards Institute 2017BS ISO 18587:2017: Translation Services. Post-Editing of Machine Translation Output. Requirements.
    [Google Scholar]
  4. Cleff, Thomas
    2014Exploratory Data Analysis in Business and Economics: An Introduction Using SPSS, Stata, and Excel. Cham: Springer. 10.1007/978‑3‑319‑01517‑0
    https://doi.org/10.1007/978-3-319-01517-0 [Google Scholar]
  5. Cumbreño, Cristina, and Nora Aranberri
    2021 “What Do You Say? Comparison of Metrics for Post-Editing Effort.” InExplorations in Empirical Translation Process Research. Machine Translation: Technologies and Applications (), edited byMichael Carl, –. Cham: Springer. 10.1007/978‑3‑030‑69777‑8_3
    https://doi.org/10.1007/978-3-030-69777-8_3 [Google Scholar]
  6. ELIA, EMT, EUATC, FIT Europe, GALA, LIND, and Women in Localization
    ELIA, EMT, EUATC, FIT Europe, GALA, LIND, and Women in Localization 2022European Language Industry Survey 2022. Trends, Expectations and Concerns of the European Language Industry. AccessedSeptember 30, 2022. https://ec.europa.eu/info/sites/default/files/about_the_european_commission/service_standards_and_principles/documents/elis2022-report.pdf
    [Google Scholar]
  7. Forsyth, David
    2018Probability and Statistics for Computer Science. Cham: Springer. 10.1007/978‑3‑319‑64410‑3
    https://doi.org/10.1007/978-3-319-64410-3 [Google Scholar]
  8. IBM
    IBM 2021IBM SPSS Statistics. AccessedNovember 6, 2021. https://www.ibm.com/products/spss-statistics
    [Google Scholar]
  9. Kosmaczewska, Kasia, and Matt Train
    2019 “Application of Post-Edited Machine Translation in Fashion eCommerce.” InProceedings of Machine Translation Summit XVII Volume 2: Translator, Project and User Tracks. Dublin, Ireland, August 19–23, 2019, –. European Association for Machine Translation. AccessedOctober 2, 2020. https://www.aclweb.org/anthology/W19-6730
    [Google Scholar]
  10. Krings, Hans P.
    2001Repairing Texts: Empirical Investigations of Machine Translation Post-Editing Processes. Ohio: Kent State University Press.
    [Google Scholar]
  11. 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.” InProceedings of Machine Translation Summit XVII Volume 1: Research Track. Dublin, Ireland, August 19–23, 2019, –. European Association for Machine Translation. AccessedOctober 9, 2020. https://www.aclweb.org/anthology/W19-6626
    [Google Scholar]
  12. Library of Congress
    Library of Congress 2017Codes for the Representation of Names of Languages. AccessedJune 22, 2021. https://www.loc.gov/standards/iso639-2/php/code_list.php
    [Google Scholar]
  13. Macken, Lieve, Daniel Prou, and Arda Tezcan
    2020 “Quantifying the Effect of Machine Translation in a High-Quality Human Translation Production Process.” Informatics (): . 10.3390/informatics7020012
    https://doi.org/10.3390/informatics7020012 [Google Scholar]
  14. Mellinger, Christopher D., and Thomas A. Hanson
    2016Quantitative Research Methods in Translation and Interpreting Studies. Milton Park, Abingdon, Oxon: Routledge. 10.4324/9781315647845
    https://doi.org/10.4324/9781315647845 [Google Scholar]
  15. Memsource
    Memsource 2020Machine Translation Workshop Series: Kick-off Event Highlights. AccessedApril 22, 2022. https://www.memsource.com/blog/mt-workshop-series-kick-off-event-highlights/
    [Google Scholar]
  16. 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, (): –. 10.1007/s10590‑015‑9175‑2
    https://doi.org/10.1007/s10590-015-9175-2 [Google Scholar]
  17. Moorkens, Joss
    2020 “Translation in the Neoliberal Era.” InThe Routledge Handbook of Translation and Globalization, edited byBielsa, Esperança, and Dionysios Kapsaskis, –. London: Routledge. 10.4324/9781003121848‑27
    https://doi.org/10.4324/9781003121848-27 [Google Scholar]
  18. O’Brien, Sharon
    2011 “Towards Predicting Post-Editing Productivity.” Machine Translation (): –. 10.1007/s10590‑011‑9096‑7
    https://doi.org/10.1007/s10590-011-9096-7 [Google Scholar]
  19. PacTranz
    PacTranz 2021Realistic Translation Times Using Human Translators. AccessedNovember 16, 2021. https://www.pactranz.com/translation-times/
    [Google Scholar]
  20. Parra Escartín, Carla, and Manuel Arcedillo
    2015 “Machine Translation Evaluation Made Fuzzier: A Study on Post-Editing Productivity and Evaluation Metrics in Commercial Settings.” InProceedings of the MT Summit XV Volume 1: MT Researchers’ Track. Miami, USA, October 30 – November 3, 2015, –. AccessedFebruary 10, 2021. https://aclanthology.org/2015.mtsummit-articles.11.pdf
    [Google Scholar]
  21. Pennsylvania State University
    Pennsylvania State University 2022Project 5: Explore the Data: Normality Tests and Outlier Tests. AccessedJuly 14, 2023. https://www.e-education.psu.edu/geog586/node/678
    [Google Scholar]
  22. [Google Scholar]
  23. [Google Scholar]
  24. ProZ.com 2016bRevision Rate: 2000 Words per Hour – Really?AccessedFebruary 16, 2022. https://www.proz.com/forum/proofreading_editing_reviewing/307931-revision_rate_2000_words_per_hour_really.html
    [Google Scholar]
  25. ProZ.com 2018What Are the Realistic Expectations for Post-Edited Work?AccessedFebruary 16, 2022. https://www.proz.com/forum/post_editing_machine_translation/330430-what_are_the_realistic_expectations_for_post_edited_work.html
    [Google Scholar]
  26. Rayner, Keith, Timothy J. Slattery, and Nathalie N. Bélanger
    2010 “Eye Movements, the Perceptual Span, and Reading Speed.” Psychonomic Bulletin & Review, (): –. 10.3758/PBR.17.6.834
    https://doi.org/10.3758/PBR.17.6.834 [Google Scholar]
  27. Sánchez-Gijón, Pilar, Joss Moorkens, and Andy Way
    2019 “Post-Editing Neural Machine Translation versus Translation Memory Segments.” Machine Translation, (): –. 10.1007/s10590‑019‑09232‑x
    https://doi.org/10.1007/s10590-019-09232-x [Google Scholar]
  28. 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 () : –.
    [Google Scholar]
  29. Toral, Antonio, Martijn Wieling, and Andy Way
    2018 “Post-editing Effort of a Novel with Statistical and Neural Machine Translation.” Frontiers in Digital Humanities: –. 10.3389/fdigh.2018.00009
    https://doi.org/10.3389/fdigh.2018.00009 [Google Scholar]
  30. Virino, Virginia
    2022 “How Many Words Does a Professional Translator Translate per Day?” Pangeanic. AccessedFebruary 15, 2022. https://blog.pangeanic.com/professional-translator-translation-words-per-day
    [Google Scholar]
  31. Wicklin, Rick
    2023 “Weak or strong? How to interpret a Spearman or Kendall correlation.” SAS. AccessedOctober 5, 2023. https://blogs.sas.com/content/iml/2023/04/05/interpret-spearman-kendall-corr.html
    [Google Scholar]
/content/journals/10.1075/ts.22044.ter
Loading
/content/journals/10.1075/ts.22044.ter
Loading

Data & Media loading...

This is a required field
Please enter a valid email address
Approval was successful
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error