Potential Use of ChatGPT-4 for Translating the Emirati Dialect Into English
DOI:
https://doi.org/10.17507/tpls.1509.01Keywords:
large language model, Emirati dialect, Arabic language, Arab dialect, machine translationAbstract
For translators and conventional machine systems, Arabic dialects pose translation challenges including scarce linguistic resources and the complexity of nonstandard Arabic. However, large language models (LLMs) are able to understand contextual meaning and showcase promising translation capabilities. This study investigates ChatGPT-4’s understanding and translations of five excerpts, including 39 lexical items, from the Emirati dialect into English. The data were analyzed qualitatively for clarity, fluency, and structure. Additionally, four bilingual raters quantitatively evaluated the translated lexical items according to the context. Qualitative analysis revealed that ChatGPT-4 could understand the Emirati dialect’s linguistic, cultural, and semantic intricacies and successfully translate them into English. Quantitative evaluation, based on accuracy of meaning, word choice, naturalness, syntactic harmony, and clarity, demonstrated a high level of agreement among the raters. However, the source of the data, which was an online forum, might have impacted the results, as ChatGPT could have been trained on similar data from such forums, potentially influencing its translation outcomes. This study contributes to the discussion of LLMs’ viability in translation practice, with implications for translators, translation trainers, and tool makers.
References
Al-Batineh, M. (2023). The localization of food- and drink-related items in video games: The case of The Witcher 3 in Arabic. Digital Translation: International Journal of Translation and Localization, 10(1), 37–57.
Al-Batineh, M., & Alsmadi, R. (2021). Translator-oriented translation criticism: The case of Roger Allen’s translation of Khan al-Khalili. Jordan Journal of Modern Languages and Literatures, 13(3), 579–602. https://doi.org/ 10.47012/jjmll.13.3.11
Al-Ibrahim, R., & Duwairi, R. M. (2020). Neural machine translation from Jordanian dialect to Modern Standard Arabic. In 2020 11th International Conference on Information and Communication Systems (ICICS) (pp. 173–178). https://doi.org/10.1109/ICICS49469.2020.239505
Al Khamiri, S. (2015). Translating Emirati folklore (Unpublished master’s thesis). American University of Sharjah.
Al Qassimi, S. R. A. (n.d.). Translating Emirati poetry. Retrieved October 3, 2024, from https://books.google.ae/books/about/Translating_Emirati_Poetry.html?id=qd-2tAEACAAJ&redir_esc=y
Albashir, T. M., Alzoubi, H., & Albatainih, M. (2020). Improving Arabic instant machine translation: The case of Arabic triangle of language. Journal of Computer Science, 16(7), 956–965. https://doi.org/10.3844/jcssp.2020.956.965
Al Tenaijy, M., & Al-Batineh, M. (2024). Translating Emirati literature: Exploring culture-specific items in Mohammed Al Murr’s Dubai Tales. Humanities and Social Sciences Communications, 11(1), 1–8. https://doi.org/10.1057/s41599-023-02555-4
Baniata, L. H., Ampomah, I. K. E., & Park, S. (2021). A transformer-based neural machine translation model for Arabic dialects that utilizes subword units. Sensors, 21(19), 6509. https://doi.org/10.3390/s21196509
Farhan, W., Abdulrahman, S., & Al-Khatib, A. (2020). Unsupervised dialectal neural machine translation. Information Processing & Management, 57(3), 102181. https://doi.org/10.1016/j.ipm.2019.102181
Gao, Y., Wang, R., & Hou, F. (2023). Unleashing the power of ChatGPT for translation: An empirical study. arXiv. https://doi.org/10.48550/arXiv.2304.02182
Harrat, S., Meftouh, K., & Smaili, K. (2019). Machine translation for Arabic dialects (Survey). Information Processing & Management, 56(2), 262–273. https://doi.org/10.1016/j.ipm.2017.08.003
Hendy, A., Abdi, H., Steinke, K., Zhang, S., Patel, N., Kurniawan, B., & Belinkov, Y. (2023, February). How good are GPT models at machine translation? A comprehensive evaluation. Retrieved October 3, 2024, from https://arxiv.org/abs/2302.09210v1
Karpinska, M., & Iyyer, M. (2023). Large language models effectively leverage document-level context for literary translation, but critical errors persist. In Conference on Machine Translation - Proceedings (pp. 406–438). https://doi.org/10.18653/v1/2023.wmt-1.41
Khamis, N. (2007). Translating Emirati dialect in dramatic texts (Unpublished master’s thesis). American University of Sharjah.
Landis, J. R., & Koch, G. G. (1977). The measurement of observer agreement for categorical data. Biometrics, 33(1), 159. https://doi.org/10.2307/252931
Leung, T.-C., Ntelitheos, T., & Al Kaabi, M. (2020). Emirati Arabic: A comprehensive grammar (Routledge Comprehensive Grammars). Retrieved October 3, 2024, from https://www.amazon.com/Emirati-Arabic-Comprehensive-Routledge-Grammars/dp/0367220822
Lilli, S. (2023). ChatGPT-4 and Italian dialects: Assessing linguistic competence. Umanistica Digitale, 16. https://doi.org/10.6092/issn.2532-8816/18221
Meftouh, K., Harrat, S., Abbas, M., & Smaili, K. (2015). Machine translation experiments on PADIC: A parallel Arabic dialect corpus. Retrieved October 3, 2024, from https://hal.science/hal-01261587
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (n.d.). Language models are unsupervised multitask learners. Retrieved October 3, 2024, from https://github.com/codelucas/newspaper
Sajjad, H., Abdelali, A., Durrani, N., & Dalvi, F. (2020). AraBench: Benchmarking dialectal Arabic-English machine translation. In COLING 2020 – 28th International Conference on Computational Linguistics, Proceedings of the Conference (pp. 5094–5107). https://doi.org/10.18653/v1/2020.coling-main.447
Salloum, W., & Habash, N. (2013). Dialectal Arabic to English machine translation: Pivoting through Modern Standard Arabic. Retrieved October 3, 2024, from https://aclanthology.org/N13-1036.pdf
Salloum, W., & Habash, N. (2022, March). Unsupervised Arabic dialect segmentation for machine translation. Natural Language Engineering, 28(2), 223–248. https://doi.org/10.1017/S1351324920000455
Sghaier, M. A., & Zrigui, M. (2020, January). Rule-based machine translation from Tunisian dialect to Modern Standard Arabic. Procedia Computer Science, 176, 310–319. https://doi.org/10.1016/j.procs.2020.08.033
Slim, A., Melouah, A., Faghihi, U., & Sahib, K. (2022). Improving neural machine translation for low-resource Algerian dialect by transductive transfer learning strategy. Arabian Journal for Science and Engineering, 47(8), 10411–10418. https://doi.org/10.1007/s13369-022-06588-w
Zbib, R., Malchiodi, E., Devlin, J., Stallard, D., Matsoukas, S., Schwartz, R., Makhoul, J., Zaidan, O. F., & Callison-Burch, C. (2012). Machine translation of Arabic dialects. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 49–59). Association for Computational Linguistics. Retrieved January 17, 2025, from https://aclanthology.org/N12-1006/
