Poetry is the Last Resort of Translation in the Age of Artificial Intelligence
DOI:
https://doi.org/10.53286/arts.v7i3.2710Keywords:
Poetry translation, Artificial Intelligence, Error severity, Human translationAbstract
This study investigates the potential and limitations of artificial intelligence (AI) in translating poetry from English to Arabic compared to human translations. Focusing on Khalil Gibran’s Sand and Foam, the research compares a human-translated version by Antonious Basheer with an AI-generated version produced by ChatGPT-4. Using Multidimensional Quality Metrics (MQM) and qualitative assessments, the study analyzes accuracy and fluency, reflecting the poetic fidelity of both translations. Findings reveal that while ChatGPT-4 excels in grammatical consistency and structural clarity, it often lacks emotional depth, stylistic features, and cultural resonance in human translation. Conversely, although more expressive, the human version contains notable inconsistencies and errors. The results highlight both AI's promise and current limitations in literary reproduction, advocating for a hybrid approach that combines AI efficiency with human creativity. Ultimately, this research contributes to a deeper understanding of poetic translation and offers pathways to enhance AI’s role in preserving literary artistry.
Downloads
References
AlAfnan, M. A., & Alshakhs, T. (2025). Bridging linguistic and cultural nuances: A comparative study of human and AI translations of Arabic dialect poetry. Advances in Artificial Intelligence and Machine Learning, 5(1), 3236–3260. https://doi.org/10.54364/AAIML.2025.51186
Algobaei, F., Alzain, E., Naji, E., & Nagi, K. A. (2024). Gender Issues between Gemini and ChatGPT: The Case of English-Arabic Translation. World Journal of English Language, 15(1), 9. https://doi.org/10.5430/wjel.v15n1p9
Alowedi, N., & Al-Ahdal, A. (2023). Artificial intelligence based Arabic-to-English machine versus human translation of poetry: An analytical study of outcomes. Journal of Namibian Studies: History Politics Culture, (33). https://doi.org/10.59670/jns.v33i.800
Alzain, E., Nagi, K. A., & AlGobaei, F. (2024). The quality of Google Translate and ChatGPT English to Arabic translation: The case of scientific text translation. Forum for Linguistic Studies, 6(3), 837–849. https://doi.org/10.30564/fls.v6i3.6799
Bahrami, N. (2012). Strategies used in the translation of allusions in Hafiz Shirazi's poetry. Journal of Language and Culture, 3(1), 1–9. https://doi.org/10.5897/JLC11.058
Balasubramanian, S. (2023). Exploring the capabilities of ChatGPT in natural language processing tasks. Journal of Artificial Intelligence and Machine Learning, 2(1), 717. https://doi.org/10.17605/OSF.IO/XJYMQ
Bassnett, S. (2014). The translator as mediator of poetic meaning. Meta: Journal des Traducteurs, 59(1), 1–15.
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., & Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, (33), 1877–1901.
Buçpapaj, E., & Koni, E. (2024). "The Art of Fidelity and Creativity in Literary Translation. Scope Journal, 14(04), 974–985.
Cai, Z. G., Duan, X., Haslett, D. A., Wang, S., & Pickering, M. J. (2023). Do large language models resemble humans in language use? arXiv preprint arXiv: 2303.08014.
Chakrabarty, T., Saakyan, A., & Muresan, S. (2021). Don't go far off: An empirical study on neural poetry translation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (pp. 577). https://doi.org/10.18653/v1/2021.emnlp-main.577
Christiano, P. F., Leike, J., Brown, T. B., Martic, M., Legg, S., & Amodei, D. (2017). Deep reinforcement learning from human preferences. In Advances in Neural Information Processing Systems 30 (NIPS 2017) (pp. 4302–4310). Curran Associates, Inc. https://doi.org/10.5555/3294996.3295184
Dai, J., Shen, H., et al. (2022). The differences between machine translation and human translation from the perspective of literary texts. International Journal of Arts and Social Science, 5(10), 112–133.
Edgerton, D. (2023). A brief history of tech skepticism. Strategy+Business. https://www.strategy-business.com/article/A-brief-history-of-tech-skepticism
Fasiullah, S. M. (2019). Challenges in translating poetry: A study of two English poems translated in Urdu by Muhammad Iqbal. Universal Review.
Freitag, M., Foster, G., Grangier, D., Ratnakar, V., Tan, Q., & Macherey, W. (2021). Experts, errors, and context: a large scale study of human evaluation for machine translation. Transactions of the Association for Computational Linguistics, 9, 742–758. https://doi.org/10.1162/tacl_a_00437
Floridi, L. (2019). Artificial intelligence, human intelligence, and the future of work. Philosophy & Technology, 32(4), 545–559. https://doi.org/10.1007/s13347-019-00351-0
Frost, W. (1969). Dryden and the art of translation. Yale University Press.
Gao, R. Y., Lin, Y., Zhao, N., & Cai, Z. G. (2024). Machine translation of Chinese classical poetry: A comparison among ChatGPT, Google Translate, and DeepL Translator. Humanities and Social Sciences Communications, (11), Article 835. https://doi.org/10.1057/s41599-024-03363-0
Ghazvininejad, M., Choi, Y., & Knight, K. (2018). Neural poetry translation. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) (pp. 67–71). Association for Computational Linguistics. https://doi.org/10.18653/v1/N18-2011
Gibran, K. (1926). Sand and foam. Alfred A. Knopf.
Gibran, K. G. (1926–2020). Sand and foam (A. Basheer, Trans.). Hindawi.
Hendy, A., Abdelrehim, M., Sharaf, A., Raunak, V., Gabr, M., Matsushita, H., & Awadalla, H. H. (2023). How good are GPT models at machine translation? A comprehensive evaluation. arXiv preprint arXiv:2302.09210.
Humblé, P. (2019). Machine translation and poetry: The case of English and Portuguese. Ilha do Desterro, (72), 41–56. https://doi.org/10.5007/2175-8026.2019v72n2p41
Jiao, W., Wang, W., Huang, J. T., & Wang, X., Tu, Z. (2023). Is ChatGPT a good translator? A preliminary study. arXiv preprint arXiv:2301.08745.
Jones, F. R. (2011). Translating poetry: The role of the translator as interpreter and creator. Translation Studies, 4(2), 177–190. https://doi.org/10.1080/14781700.2011.584099
Khalifa, A. A. (2015). Translation studies: Some problematic aspects of Arabic poetry translation. International Journal of Sciences: Basic and Applied Research (IJSBAR), 19(1), 314–324.
Kuzman, T., Vintar, Š., & Arcan, M. (2019). Neural machine translation of literary texts from English to Slovene. In Proceedings of the qualities of literary machine translation (pp. 1–9). https://aclanthology.org/W19-7301.pdf
Lahiani, R. (2022). Aesthetic poetry and creative translations: A translational hermeneutic reading. Humanities and Social Sciences Communications, 9(1), 1–9. https://doi.org/10.1057/s41599-022-01481-1
Lommel, A. (2018). Metrics for evaluating translation quality: A case for standardising error classifications. In Evaluation of Translation Quality (pp. 109–127). Springer. https://doi.org/10.1007/978-3-319-91241-7_6
Lommel, A., Uszkoreit, H., & Burchardt, A. (2014). Multidimensional quality metrics (MQM): A framework for specification describing metrics for translation quality. Tradumàtica, 12, 455–463. https://doi.org/10.5565/rev/tradumatica.Issue23
Lefevere, A. (1992). Translation, rewriting, and the manipulation of literary fame. Routledge.
Läubli, S., Castilho, S., Neubig, G., et al. (2020). A set of recommendations for assessing human–machine parity in language translation. Journal of Artificial Intelligence Research, 67. https://doi.org/10.1613/jair.1.11371
Ma, Y., & Wang, B. (2020). Description and quality assessment of poetry translation: Application of a linguistic model. Contrastive Pragmatics, 3(1), 89–111. https://doi.org/10.1163/26660393-bja10015
Mariana, V. T., Cox, T., & Melby, A. (2015). The multidimensional quality metrics (MQM) framework: A new framework for translation quality assessment. The Journal of Specialised Translation, 23, 137–161. https://doi.org/10.26034/cm.jostrans.2015.343
Mittelstadt, B. D. (2019). Principles alone cannot guarantee ethical AI. Nature Machine Intelligence, 1(11), 501–507. https://doi.org/10.1038/s42256-019-0114-4
Moslem, Y., Haque, R., & Way, A. (2023). Adaptive machine translation with large language models. arXiv preprint arXiv:2301.13294.
Motair, A. A. A., Algobaei, F., & Alhazmi, M. D. (2025). Ethics in Translation: A Pathway to Integrity in Future Professionals. Arts for Linguistic & Literary Studies, 7(1), 711–732. https://doi.org/10.53286/arts.v7i1.2417
Naghiyeva, S. B. (2015). Does poetry lose or gain in translation? English Language and Literature Studies, 5(3). Canadian Center of Science and Education.
Nagi, K.A., Alzain, E., Naji, E., 2024. Informed prompts and improving ChatGPT English to Arabic translation. Al-Andalus Journal for Humanities & Social Sciences. 98(11). https://doi.org/10.35781/1637-000-098-007
Nair, S. K. (2018). Is poetry lost in translation? Samyukta: A Journal of Gender and Culture, 3(1), 35–42. https://doi.org/10.53007/SJGC.2018.V3.I1.118
Newmark, P. (1991). About translation. Multilingual Matters.
Nida, E., & Taber, C. (1982). The theory and practice of translation. Brill.
Niknasab, L. (2011). Translation and culture: Allusions as culture bumps. SKASE Journal of Translation and Interpretation, 5(1), 45–54. Retrieved from https://www.skase.sk/Volumes/JTI05/pdf_doc/03.pdf
Ono, K. (2019). Replacement of the military's intellectual labor using artificial intelligence — Discussion about AI and human co-existence. National Institute for Defense Studies Bulletin, (1), 3–20. https://www.nids.mod.go.jp/english/publication/kiyo/pdf/2019/bulletin_e2019_1.pdf
Othman, A. A. M. (2023). Cohesion and coherence for poetry interpretation and translation. AWEJ for Translation & Literary Studies, 7(2), 176–196. https://doi.org/10.24093/awejtls/vol7no2.13
Ovidiu, M. (2008). Translating poetry: Contemporary theories and hypotheses. Professional Communication and Translation Studies, 1. Lucian Blaga University of Sibiu. https://doi.org/10.59168/YDRF2520
Peng, N., Li, W., Yang, B., & Li, Z. (2023). Exploring ChatGPT for automatic poetry generation. Journal of Artificial Intelligence Research, 72, 215–237. https://doi.org/10.1613/jair.1.13208
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI blog, 1(8), 9.
Radmir, K., Anton, K., Aleksandr, A., Dmitry, A., & Oleg, V. (2024). Comparison of ChatGPT and Bard for using in hybrid intelligent information systems. E3S Web of Conferences. https://doi.org/10.1051/e3sconf/202454908009
Raffel, B. (2010). The Art of Translating Poetry. Penn State Press.
Schulman, J., Zoph, B., Kim, C., Hilton, J., Menick, J., Weng, J., & Ryder, N. (2022). ChatGPT: Optimizing language models for dialogue. OpenAI blog. https://openai.com/blog/chatgpt
Seljan, S., Dunder, I., & Pavlovski, M. (2020). Human quality evaluation of machine-translated poetry. In 2020 43rd International Convention on Information, Communication and Electronic Technology (MIPRO) (pp. 1040–1045). IEEE. https://doi.org/10.23919/MIPRO48935.2020.9245436
Soong, S. C. (1973). Notes on translating poetry. In W. Arrowsmith & R. Shattuck (Eds.), The craft and context of translation (pp. xx–xx). Doubleday Anchor Books.
Studzińska, J. (2020). Turing test for (automatic) translation of poetry (Polish). Porównania, (26), 299–313. https://doi.org/10.14746/por.2020.1.17
Tahir, E. M. (2008). Strategies for translating poetry aesthetically. https://doi.org/10.13140/RG.2.2.22475.28961
Toral, A., Castilho, S., Hu, K., et al. (2018). Attaining the unattainable? Reassessing claims of human parity in neural machine translation. In Proceedings of the Third Conference on Machine Translation: Research Papers. https://doi.org/10.18653/v1/w18-6312
Tymoczko, M. (2017). Expanding translation, empowering translators. The Translator, 23(1), 1–15. https://doi.org/10.1080/13556509.2017.1288257
Vardaro, J., Schaeffer, M., & Hansen-Schirra, S. (2019). Translation quality and effort prediction in professional machine translation post-editing. In M. Carl, M. Schaeffer, & S. Hansen-Schirra (Eds.), Proceedings of the Second MEMENTO Workshop on Modelling Parameters of Cognitive Effort in Translation Production (pp. 7–8). European Association for Machine Translation. https://doi.org/10.18653/v1/W19-7004
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems, 30, 5998–6008.
Venuti, L. (1998). Poetry and translation. The Translator, 4(2), 145–166. https://doi.org/10.1080/13556509.1998.10799088
Venuti, L. (2000). The translation studies reader. Routledge.
Wang, L. (2023). The impacts and challenges of artificial intelligence translation tool on translation professionals. SHS Web of Conferences. https://www.shsconferences.org/articles/shsconf/pdf/2023/12/shsconf_icssed2023_02021.pdf
West, D. M. (2018). The future of work: Robots, AI, and automation. Brookings Institution Press.
Zequeira, M. (2024). Artificial intelligence as a combat multiplier: Using AI to unburden army staffs. Military Review Online Exclusive. U.S. Army University Press.
Zhang, Y., Sun, A., Rao, J., & Huang, J. (2023). Evaluating large language models in creative writing: The case of story generation. Transactions of the Association for Computational Linguistics, 11, 123–138. https://doi.org/10.1162/tacl_a_00434
Zhang, Y., & Wang, L. (2024). Machine translation of Chinese classical poetry: A comparison of ChatGPT and traditional systems. Humanities and Social Sciences Communications, (11), Article 363.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright and Licensing
copyright is retained by the authors. Articles are licensed under an open access Creative Commons CC BY 4.0 license, meaning that anyone may download and read the paper for free. In addition, the article may be reused and quoted provided that the original published version is cited. These conditions allow for maximum use and exposure of the work.
