In-Context Learning for Low-Resource Machine Translation: A Study on Tarifit with Large Language Models
Open Access
- 6 August 2025
- journal article
- research article
- Published by MDPI AG in Algorithms
- Vol. 18 (8) , 489
Abstract
This study presents the first systematic evaluation of in-context learning for Tarifit machine translation, a low-resource Amazigh language spoken by 5 million people in Morocco and Europe. We assess three large language models (GPT-4, Claude-3.5, PaLM-2) across Tarifit–Arabic, Tarifit–French, and Tarifit–English translation using 1000 sentence pairs and 5-fold cross-validation. Results show that 8-shot similarity-based demonstration selection achieves optimal performance. GPT-4 achieved 20.2 BLEU for Tarifit–Arabic, 14.8 for Tarifit–French, and 10.9 for Tarifit–English. Linguistic proximity significantly impacts translation quality, with Tarifit–Arabic substantially outperforming other language pairs by 8.4 BLEU points due to shared vocabulary and morphological patterns. Error analysis reveals systematic issues with morphological complexity (42% of errors) and cultural terminology preservation (18% of errors). This work establishes baseline benchmarks for Tarifit translation and demonstrates the viability of in-context learning for morphologically complex low-resource languages, contributing to linguistic equity in AI systems.Keywords
This publication has 23 references indexed in Scilit:
- Exploring data augmentation for Amazigh speech recognition with convolutional neural networksInternational Journal of Speech Technology, 2024
- Automatic translation from English to Amazigh using transformer learningIndonesian Journal of Electrical Engineering and Computer Science, 2024
- Amazigh Language Use on Social Media: An Exploratory StudyJURNAL ARBITRER, 2023
- APMorph: finite-state transducer for Amazigh pronominal morphologyInternational Journal of Electrical and Computer Engineering (IJECE), 2021
- Toward an automatic speech recognition system for amazigh-tarifit languageInternational Journal of Speech Technology, 2019
- Towards UNL-based machine translation for Moroccan Amazigh languageInternational Journal of Computational Science and Engineering, 2018
- Indigenous language revitalization, promotion, and education: function of digital technologyComputer Assisted Language Learning, 2016
- AmAMorph: Finite State Morphological Analyzer for AmazigheJournal of Computing and Information Technology, 2016
- ‘We are all beginners’: Amazigh in language policy and educational practice in MoroccoCompare: A Journal of Comparative and International Education, 2011
- Processing Amazighe LanguageLecture Notes in Computer Science, 2011