AI-BASED TRANSLATION QUALITY FOR LOW-RESOURCE LANGUAGES: THE CASE OF MALTESE

Sergio Portelli

Abstract


Maltese is the national language of the Republic of Malta and shares its official language status with English. Despite being used by a small community mostly in oral communication and in a few formal domains, it became an official language of the European Union in 2004. In the last two decades, because of EU membership, translation requirements in Maltese have greatly increased. However, the relative scarcity of Maltese texts in many domains, especially in technical fields, has created a critical data deficiency for training large language models (LLMs).  Hence, the quality of AI-driven translation for Maltese is generally perceived to be inadequate. However, to date, no studies have been made to assess translation quality related to the use of AI-based technologies for the Maltese language. To address this research gap, the present small-scale study evaluates the performance of two prominent AI-based translation tools, Google Translate and ChatGPT, on a 6000-word corpus of 20 texts translated from Italian into both Maltese and English. The raw output was systematically evaluated using an adapted DQF-MQM error typology template. The results show that in the case of Maltese, Google Translate made almost three times more errors with respect to English, while ChatGPT generated over seven times the errors for Maltese. The analysis concludes that despite the high status of Maltese in the EU’s multilingual setting, the limitations of Maltese as a low-resource language still persist, and a highly cautious approach must be taken by Maltese translators and post-editors when using AI-based tools for translation.

Keywords


Maltese, artificial intelligence, translation, error analysis

Full Text:

PDF

References


All Top Everything. (2025, October 9). Top 10 most used AI chatbots in the world (2025). All Top Everything. https://www.alltopeverything.com/most-used-ai-chatbots/ (last access 20 February 2026).

Ethnologue. (2025). Maltese (mlt). SIL Global. Retrieved June 2, 2026, from https://www.ethnologue.com/language/mlt/ (last access 10 November 2025).

Maltese Language Resource Server. (n.d.). MLRS corpora. University of Malta. Retrieved June 2, 2026, from https://mlrs.research.um.edu.mt/index.php?page=corpora (last access 4 March 2026).

Al-Romany, Tahseen and Maryam Jawad Kadhim. 2024. ‘Artificial Intelligence Impact on Human Translation: Legal Texts as a Case Study’. International Journal of Linguistics, Literature and Translation 7: 89-95. https://doi.org/10.32996/ijllt.2024.7.5.11

Bhattacharja, Joydeep. 2026. ‘Google Translate Statistics & Trends’. Retrieved from https://seosandwitch.com/google-translate-statistics/#rtoc-1 (last access 20 February 2026).

Cieri, Christopher, Mike Maxwell, Stephanie Strassel, and Jennifer Tracey. 2016. ‘Selection Criteria for Low Resource Language Programs’. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16). Portorož, Slovenia: European Language Resources Association (ELRA), p. 4543–4549. Retrieved from https://aclanthology.org/L16-1720/

Dranch, Konstantin. n.d. ‘Tools for Data Labelling in Machine translation Evaluations’. Retrieved from https://custom.mt/tools-for-data-labelling-in-machine-translation-evaluations/

Eszenyi, Réka, Klaudia Bednárová-Gibová and Edina Robin. 2023. ‘Artificial Intelligence, Machine Translation & Cyborg Translators: A Clash of Utopian and Dystopian Visions’. Orbis Linguarum 21.2: 102-113. https://doi.org/10.37708/ezs.swu.bg.v21i2.13

Goyle, Vakul, Parvathy Krishnaswamy, Kannan Girija Ravikumar, Utsa Chattopadhyay and Kartikay Goyle. 2023. ‘Neural Machine Translation for Low Resource Languages’. https://doi.org/10.1145/3567592

Hendy, Amr, Mohamed Abdelrehim, Amr Sharaf, Vikas Raunak, Mohamed Gabr, Hitokazu Matsushita, Young Jin Kim, Mohamed Afify and Hany Awadalla. 2023. ‘How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation’. https://doi.org/10.48550/arXiv.2302.09210

Il-Kunsill Nazzjonali tal-Ilsien Malti [National Council for the Maltese Language]. 2021. The State of the Maltese Language: National Survey 2021. https://kunsilltalmalti.gov.mt/wp-content/uploads/2023/03/rizultati-stharrig2021_MT-EN.pdf (last access 10 November 2025).

Karabayeva, Irina S. and Anna N. Kalizhanova. 2024. ‘Evaluating machine translation of literature through rhetorical analysis’. Journal of Translation and Language Studies 5(1): 1-9. https://doi.org/10.48185/jtls.v5i1.962

Kemp, David. 2025. ‘Digital 2026: Malta’. https://datareportal.com/reports/digital-2026-malta (last access 11 March 2026).

Mohamed, Yasir A., Akbar Kannan, Mohamed Bashir, Abdul Hakim Mohamed, Mousab A. E. Adiel and Muawia A. Elsadig. 2024. ‘The Impact of Artificial Intelligence on Language Translation: A Review’, IEEE Access 12: 25553-25579. https://doi.org/10.1109/ACCESS.2024.3366802

Moneus, Ahmed Mohammed and Yousef Sahari. 2024. ‘Artificial intelligence and human translation: A contrastive study based on legal texts’. Heliyon 10: 1-14. https://doi.org/10.1016/j.heliyon.2024.e28106

National Statistics Office. 2024. Malta Skills Survey 2022. Malta: National Statistics Office, 129.

Portelli, Sergio. 2025. ‘Terminology Development for Lesser-Used Languages in Bilingual Contexts: The Maltese Case’. In R. Resi and F. Steurs (eds). Handbook of Terminology. Terminology Planning in Europe. Amsterdam-Philadelphia: Benjamins, 653-669. https://doi.org/10.1075/hot.4.ter22

Shahmerdanova, Roya. 2025. ‘Artificial Intelligence in Translation: Challenges and Opportunities’. Acta Globalis Humanitatis et Linguarum 2(1): 62-70. https://doi.org/10.69760/aghel.02500108

Shormani, Mohammed Q. 2025. ‘Artificial intelligence contribution to translation industry: looking back and forward’. https://doi.org/10.1007/s44163-025-00487-3

Smith, Brad. 2025. ‘Unlocking data to advance European commerce and culture’. https://blogs.microsoft.com/on-the-issues/2025/07/20/eudigitalunlock/




DOI: http://dx.doi.org/10.46827/ejmts.v6i1.715

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

The research works published in this journal are free to be accessed. They can be shared (copied and redistributed in any medium or format) and\or adapted (remixed, transformed, and built upon the material for any purpose, commercially and\or not commercially) under the following terms: attribution (appropriate credit must be given indicating original authors, research work name and publication name mentioning if changes were made) and without adding additional restrictions (without restricting others from doing anything the actual license permits). Authors retain the full copyright of their published research works and cannot revoke these freedoms as long as the license terms are followed.

Copyright © 2020-2026. European Journal of Multilingualism and Translation Studies (ISSN 2734 - 5475 / ISSN-L 2734 - 5475). All rights reserved.

This journal is a serial publication uniquely identified by an International Standard Serial Number (ISSN) serial number certificate issued by Romanian National Library. All the research works are uniquely identified by a CrossRef DOI digital object identifier supplied by indexing and repository platforms. All the research works published on this journal are meeting the Open Access Publishing requirements and standards formulated by Budapest Open Access Initiative (2002), the Bethesda Statement on Open Access Publishing (2003) and  Berlin Declaration on Open Access to Knowledge in the Sciences and Humanities (2003) and can be freely accessed, shared, modified, distributed and used in educational, commercial and non-commercial purposes under a Creative Commons Attribution 4.0 International License. Copyrights of the published research works are retained by authors.