In-Context Learning for Low-Resource Machine Translation: A Study on Tarifit with Large Language Models
Guardado en:
| Udgivet i: | Algorithms vol. 18, no. 8 (2025), p. 489-508 |
|---|---|
| Hovedforfatter: | |
| Andre forfattere: | |
| Udgivet: |
MDPI AG
|
| Fag: | |
| Online adgang: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Tags: |
Ingen Tags, Vær først til at tagge denne postø!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3243965753 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 1999-4893 | ||
| 024 | 7 | |a 10.3390/a18080489 |2 doi | |
| 035 | |a 3243965753 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 231333 |2 nlm | ||
| 100 | 1 | |a Akallouch Oussama | |
| 245 | 1 | |a In-Context Learning for Low-Resource Machine Translation: A Study on Tarifit with Large Language Models | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a 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. | |
| 653 | |a Error analysis | ||
| 653 | |a Language | ||
| 653 | |a French language | ||
| 653 | |a Dictionaries | ||
| 653 | |a English language | ||
| 653 | |a Datasets | ||
| 653 | |a Errors | ||
| 653 | |a Morphology | ||
| 653 | |a Machine translation | ||
| 653 | |a Terminology | ||
| 653 | |a Endangered languages | ||
| 653 | |a Morphological analysis | ||
| 653 | |a Vocabulary | ||
| 653 | |a Business metrics | ||
| 653 | |a Grammar | ||
| 653 | |a Linguistics | ||
| 653 | |a Learning | ||
| 653 | |a Large language models | ||
| 653 | |a Arabic language | ||
| 653 | |a Voice recognition | ||
| 653 | |a Proximity | ||
| 653 | |a Languages | ||
| 653 | |a Preservation | ||
| 653 | |a Berber languages | ||
| 653 | |a Natural language processing | ||
| 653 | |a Multilingualism | ||
| 653 | |a Complexity | ||
| 653 | |a Context | ||
| 653 | |a Morphological complexity | ||
| 653 | |a Language modeling | ||
| 653 | |a Translation | ||
| 653 | |a Cultural heritage | ||
| 700 | 1 | |a Fardousse Khalid | |
| 773 | 0 | |t Algorithms |g vol. 18, no. 8 (2025), p. 489-508 | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3243965753/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3243965753/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3243965753/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |