Low-Code/No-Code AI for Machine Translation: Democratising Generative AI for Blue Transformation
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti251475 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Mercedes Arguello Casteleiro und 10 weiteren Autor:innen. Beteiligte Einrichtung: BCS SGAI, UK. Hauptthemen laut MEDLINE: Generative Artificial Intelligence, Translating, Natural Language Processing.
Abstract (Originalsprache)
Background
Malnutrition and disease affect human health. Planetary Health emerges as a cross-disciplinary field, emphasising the interconnection of human health and the health of planet Earth. The Blue Transformation is an ambitious strategy for the transformation of aquatic food systems worldwide, aiming to eradicate hunger and poverty and improving the living standards of all.
Objective
This study investigates if neural Machine Translation (MT) with generative Artificial Intelligence (AI) may reduce the language barriers, promoting access to relevant information, such as the key terms underpinning the Blue Transformation.
Methods
This study evaluates the quality of MT for a Blue Transformation dataset (a multilingual glossary of 188 term pairs and an English vocabulary of 217 unique terms and phraseological expressions) using automatic quality metrics and human judgment to assess the semantic quality (adequacy) of MT. We introduced a low-code/no-code AI approach to MT using open-source python libraries and open-source (free of charge) Large Language Models (LLMs), including multimodal LLMs that can produce content (text or speech) as output (generative AI) for text translation.
Results
The study confirms the viability of the low-code/no-code AI approach presented to MT using three lines of python code, revealing a moderate agreement among the three experts about the relative high- quality of fully automated MT with Facebook’s SeamlessM4T.
Conclusion
Our findings aligned with the 2024 AI index report about the lower performance of open-source LLMs in comparison with closed-source LLMs, e.g. OpenAI’s GPT4.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- BCS SGAI, UK.
- University of Stirling, UK.
- Universidad Politécnica de Madrid, Spain.
- Universidad de Salamanca, Spain.
- University of Southampton, UK.
- University of Salford, UK.
Zitieren
APA
Arguello Casteleiro, M., Li, S., Andrades Moreno, A., Maroto, N., Fernandez Vivanco, A., Chang, Y., Fernandez Prieto, M. J., Nguyen, N. T., Huang, Q., Furmston, T., & Keane, J. (2025). Low-Code/No-Code AI for Machine Translation: Democratising Generative AI for Blue Transformation. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti251475
Vancouver
Arguello Casteleiro M, Li S, Andrades Moreno A, Maroto N, Fernandez Vivanco A, Chang Y, et al. Low-Code/No-Code AI for Machine Translation: Democratising Generative AI for Blue Transformation. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti251475
BibTeX
@article{ArguelloCasteleiro2025,
author = {Arguello Casteleiro, Mercedes and Li, Saihong and Andrades Moreno, Arsenio and Maroto, Nava and Fernandez Vivanco, Andrea and Chang, Yifan and Fernandez Prieto, Maria Jesus and Nguyen, Ngoc Tuan and Huang, Quancan and Furmston, Tim and Keane, John},
title = {Low-Code/No-Code AI for Machine Translation: Democratising Generative AI for Blue Transformation},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti251475}
}
EUVIMED