EQUIVALENCE PROBLEMS FOUND IN MACHINE TRANSLATION OUTPUT: INSIGHTS FROM POST-EDITING ANALYSIS

Dwi Indarti, Vera Nurlia


Abstract


This study examines post-editing strategies and equivalence problems in Google Translate (GT) outputs of a non-literary text, International Relations Theory by Ferreira (2017). Focusing on the English–Indonesian translation, the analysis is limited to five levels of equivalence proposed by Baker (2018): word, above-word, grammatical, textual, and pragmatic. Using a qualitative descriptive approach supported by LF Aligner, AntConc, and AntPConc, the study identifies equivalence problems in a parallel corpus. The findings reveal frequent word-level issues, particularly loanwords and lexical mismatches, requiring paraphrasing and cultural substitution. Problems also occur at the above-word and grammatical levels, including idiomatic expressions, collocations, singular–plural mismatches, and passive constructions. Textual issues relate to cohesion gaps, while pragmatic problems are less frequent but involve implicit meaning loss. Overall, GT performs better with high-frequency nouns, adjectives, and adverbs than with verbs. The study highlights the importance of post-editing machine translation (PEMT) and recommends its integration into translation curricula to enhance linguistic competence, digital literacy, and professional readiness in AI-assisted translation contexts.

Keywords


equivalence; machine translation; non-literary text; post-editing

Full Text:

PDF

References


Alfian. (2022). English-Indonesian google translate result in J.K Rowling’s Harry Potter and The Order of the Phonenix: Analysis of non-equivalence problem. Journal Education and Development, 10(2), 415–420. DOI: https://doi.org/10.37081/ed.v10i2

Alkatheery, E. R. (2023). Google translate errors in legal texts: Machine translation quality assessment. AWEJ for Translation & Literary Studies, 7(1), 208–219. DOI: http://dx.doi.org/10.24093/awejtls/vol7no1.16

Amarasinghe, H., & Senevirathne, H. H. (2020). A comparative study on the different perspectives of technical translation: Influence of technical terms in defining technical translation with special reference to selected English non-literary documents. International Journal of Research and Innovation in Social Science, 4(6), 551–555. https://doi.org/10.1080/0907676X.2002.9961449

Baker, M. (2011). In other words: A coursebook on translation (2nd ed). Routledge.

Baker, M. (2018). In other words: A coursebook on translation (3nd Ed). Routledge.

Baker, M., & Saldanha, G. (Eds.). (2020). Routledge encyclopedia of translation studies (3rd ed.). Routledge.

Daems, J., Vandepitte, S., Hartsuiker, R. J., & Macken, L. (2017). Identifying the machine translation error types with the greatest impact on post-editing effort. Frontiers in Psychology, 8(12), 1–15. https://doi.org/10.3389/fpsyg.2017.01282

Dordevic, J. P. (2017). Translation techniques revisited: The applicability of existing solutions in non-literary translation. Facta Universitatis, 15(1), 35–47. DOI:10.22190/FULL1702035D

Farkas, A. (2023). The prevalence of self injury in adolescence: A systematic review and meta analysis. European Child & Adolescent Psychiatry. 33. 3439-3458. https://doi.org/10.1007/s00787-023-02264-y

Ferreira, M. F. (2017). Critical theory. In S. McGlinchey, R. Walters & C. Scheinpflug (Eds). International Relations Theory (pp. 49-55). Bristol: E-International Relations Publishing.

Harto, S., Hamied, F. A., Musthafa, B., & Setyarini, S. (2022). Exploring undergraduate students’ experiences in dealing with post-editing of machine translation. Indonesian Journal of Applied Linguistics, 11(3), 696–707. DOI: https://doi.org/10.17509/ijal.v11i3.42825

Hasyim. M., Saleh, F., Yusuf, R., & Abbas, A. (2021). Artificial intelligence: Machine translation accuracy in translating French-Indonesian Culinary Texts. IJACSA (International Journal of Advanced Computer Science and Applications, 12(3), 186–191. DOI:10.14569/IJACSA.2021.0120323

Hidayat, T., Nababan, M.R., & D. (2019). The shift process in transtivity system on obama’s and trump’s inauguration speech: A Translation Study. Humaniora, 31(2), 211–220. DOI:10.22146/jh.v31i2.34901

Jia, Y., Carl, M., & Wang, X. (2019). How does the post-editing of neural machine translation compare with from-scratch translation? A product and process study. The Journal of Specialised Translation, 31, 60–86. DOI:10.26034/cm.jostrans.2019.177

Karibayeva, A., Karyukin, V., Turgynbayeva, A., & Turarbek, A. (2021). The translation quality problems of machine translation systems for the Kazakh language. Journal of Mathematics, Mechanics, and Computer Science, 3(111), 132–139. DOI: https://doi.org/10.26577/JMMCS.2021.v111.i3.11

Lihua, Z. (2022). The relationship between machine translation and human translation under the influence of artificial intelligence machine translation. Mobile Information Systems, 1–8. DOI:10.1155/2022/9121636

Munkova, D., Munk, M., Benko, L., & Stastny, J. (2021). MT evaluation in the context of language complexity. Complexity, 1, 2806108. DOI:10.1155/2021/2806108

Nufus, T. Z. (2022). Analysis of translation problems arising from non-equivalence at word level, above word level, grammatical level, textual level and pragmatic level based on JK Rowling manuscript of “Harry Potter.” Journal of Positive School Psychology, 6(6), 2587–2594. https://journalppw.com/index.php/jpsp/article/download/7662/7516/1373

O’Brien, S., Balling, L. W., Carl, M., Simard, M., & Specia, L. (2012). Post-editing of machine translation: Processes and applications. Cambridge Scholar Publishing

Popović, M. (2018). Error classification and analysis for machine translation quality assessment. In J. Moorkens, S. Castilho, F. Gaspari, & S. Doherty (Eds.), Translation Quality Assessment: From Principles to Practice (pp. 129–158). Springer. https://doi.org/10.1007/978-3-319-91241-7_7

Rustandi, A., Syafryadin, Febriani, R. B. (2021). Word level, above level, grammtical level, textual, pragmatics level non-equivalene: Problem and strategy. Journal of Development and Innovation in Language and Literature Education, 1(4), 423–433. DOI:10.52690/jadila.v1i4.155

Sayogie, F., Supardi, M. (2021). Equivalence levels of literary corpus translation using a freeware analysis toolkit. Buletin Al-Turas, 27(1), 55–70. DOI:10.15408/bat.v27i1.16916

Sibuea, T. F. B., Budi, W., & Jonathan, K. (2023). The equivalence problems produced by machine translation on a literary text: A study on the Indonesian translation of Harry Potter: The Order of Phoenix. CULTURALISTICS: Journal of Cultural, Literary, and Linguistic Studies, 7(1), 1–12. DOI:10.14710/ca.v7i1.17417

Sin-Wai, C. (2017). The future of translation technology: Towards a world without babel. Routledge.

Supardi, M., Djohar, H. I., & Sayogie, F. (2021). Utilizing translation equivalence in J.K Rowling’s Harry Potter. International Journal of Linguistics, Literature and Translation, 4(5), 126–135. DOI:10.32996/ijllt.2021.4.5.12

Sycz-Opon, J., & Galuskina, K. (2017). Machine translation in the hands of trainee translators: An empirical study. Studies in Logic, Grammar and Rhetoric, 49(62), 195–212. DOI:10.1515/slgr-2017-0012

Wei, Y. (2023). Ambiguity and entropy in the process of translation and post-editing. Dublin City University.

Widya., & Ayu, D. M. I. (2015). Translation of passive voice found in the novel "The Sea of Monster by Rick Riordan and its translation by Nuraini Mastura. Lingua Cultura, 9(2), 126–131. DOI: https://doi.org/10.21512/lc.v9i2.826

Zawawi, M., & Maghfiroh, D. L. (2020). Sarcasm and the Translation Quality in The Subtle Art of Not Giving a Fuck Book. LiNGUA, 15(2), 253–260. DOI:10.18860/ling.v15i2.8913

Ziganshina, L. E., Yudina, E. V., Gabdrakhmanov, A. I., & Ried, J. (2021). Assessing human post-editing efforts to compare the performance of three machine translation engines for English to Russian translation of Chochrane plain language health information: Results of a randomised comparison. Informatics, 8(9), 1–16. DOI:10.3390/informatics8010009




DOI: https://doi.org/10.30743/ll.v10i1.12714

Refbacks

  • There are currently no refbacks.