Translating Akkadian Transliterations to English with Transfer Learning

Najat Nehme, Danielle Azar, Diana Kutsalo, Jalal Possik

2025

Abstract

Akkadian is an ancient Semitic language with a complex cuneiform script and fragmented artifacts. These attributes make the translation of text from this language to another one very challenging. In this paper, we utilize transfer learning with a model pre-trained on multiple languages to enhance the accuracy to translate from Akkadian to English. By fine-tuning this model on a curated Akkadian-English dataset, the research aims to leverage the extensive linguistic pre-training of the model in order to adapt it to Akkadian’s specificities.

Paper Citation

in Harvard Style

Nehme N., Azar D., Kutsalo D. and Possik J. (2025). Translating Akkadian Transliterations to English with Transfer Learning. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 1048-1053. DOI: 10.5220/0013257200003890

in Bibtex Style

@conference{icaart25,
author={Najat Nehme and Danielle Azar and Diana Kutsalo and Jalal Possik},
title={Translating Akkadian Transliterations to English with Transfer Learning},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2025},
pages={1048-1053},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013257200003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Translating Akkadian Transliterations to English with Transfer Learning
SN - 978-989-758-737-5
AU - Nehme N.
AU - Azar D.
AU - Kutsalo D.
AU - Possik J.
PY - 2025
SP - 1048
EP - 1053
DO - 10.5220/0013257200003890
PB - SciTePress