The Accuracy and Consistency of Machine Translation Engines: Case Study of Translating Economic & Statistical Texts from English into Arabic

Monther  Battah; Suleiman Ibrahim Shelash   Mohammad; Muhammad Turki  Alshurideh; Asokan  Vasudevan

doi:10.35516/hum.v51i4.8014

Authors

Monther Battah Department of Human Basic Sciences, Huson University College, Al-Balqa Applied University, Jordan https://orcid.org/0000-0001-9238-3114
Suleiman Ibrahim Shelash Mohammad Research follower, INTI International University, 71800 Negeri Sembilan, Malaysia; Department of Business Administration, Business School, Al al-Bayt University, Jordan https://orcid.org/0000-0001-6156-9063
Muhammad Turki Alshurideh Department of Marketing, School of Business, The University of Jordan, Amman, Jordan https://orcid.org/0000-0002-7336-381X
Asokan Vasudevan Faculty of Business and Communications, INTI International University, 71800 Negeri Sembilan, Malaysia https://orcid.org/0000-0002-9866-4045

DOI:

https://doi.org/10.35516/hum.v51i4.8014

Keywords:

Google Translate, Consistency, Accuracy, Coherence and Cohesion

Abstract

Objectives: This study assesses the precision and consistency of the Google Translate engine and tool in translating statistical and economic texts from English into Arabic.

Methods: The descriptive analytical approach was employed in this project, and the study sample consists of five texts extracted from statistical and economic research.

Results: The study revealed that the Google translation tool faced numerous challenges and contained lexical, grammatical, and consistency errors. Besides, a grand challenge might arise from the idioms and abbreviations, as Google Translate would use word-for-word translation and render them inaccurate meaning. In some cases, the abbreviations in the source text (ST) would be displayed as they are in the target text (TT), In other cases, Google Translate would do a deep search to render their meanings in the TT. Further, Google Translate has a significant problem rendering technical and specialized terms into the TT, and in some cases, it doesn’t consider the contexts and has a lexical choice challenge. Finally, Google Translate renders some terms with different meanings within the same text.

Conclusions: Idioms and abbreviations present a grand challenge, as Google Translate would use word-for-word translation and render them in an inaccurate meaning. In some cases, the abbreviations in the ST are rendered as they are in the TT, and in other cases, Google Translate would do a deep search to render their meanings in the TT.

Downloads

Download data is not yet available.

References

Automatic Language Processing Advisory Committee (ALPAC). (1966). Language and machines computers in translation and linguistics. National Academy of Sciences & the National Research Council.

Johnson, M., Schuster, M., Le, Q. V., Krikun, M., Wu, Y., Chen, Z., ...& Dean, J. (2017). Google’s multilingual neural machine translation system: Enabling zero-shot translation. Transactions of the Association for Computational Linguistics, 5, 339-351.

Koehn, P. and Knowles, R. (2017).Six Challenges for Neural Machine Translation.Proceedings of the First Workshop on Neural Machine Translation, pages 28–39, Vancouver, Canada, August 4, 2017.

Melby, A. K. (2019). Future of machine translation: Musings on Weaver's memo. The Routledge handbook of translation and technology.

Motlaq, M., & Mahadi, T. (2020).Advantages and disadvantages of using machine translation in translation pedagogy from the perspective of instructors and learners. Humanities & Social Sciences Reviews, 8(4), 121-137.

Okpor, M. D. (2014). Machine Translation Approaches Issues and Challenges. International Journal of Computer Science Issues, 11 (5), 2.

Thelen, M. (2008). Translation quality assessment or quality management and quality control of translation. Translation and meaning, 8, 411-424.

Tu, Z., Liu, Y., Shi, S., & Zhang, T. (2018). Learning to remember translation history with a continuous cache. Transactions of the Association for Computational Linguistics, 6, 407-420.

Weng, R., Wang, Q., Cheng, W., Zhu, C., & Zhang, M. (2023, June). Towards reliable neural machine translation with consistency-aware meta-learning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37, No. 11, pp. 13709-13717).