report
Gherbal: A Multilingual Classifier for Low-Resource Languages
Abstract
Conference Presentation
Presented at TIM'24, University Hassan II, Casablanca, Morocco, 2024.
This talk introduces Gherbal, a multilingual classifier built specifically for low-resource languages, addressing the gap in NLP tooling for underrepresented language communities.
Citation
Related Research
Sawtone: A Universal Framework for Phonetic Similarity and Alignment Across Languages and Scripts
Introduces a cross-script phonetic alignment framework with modular language-specific adapters. Demonstrates 88% BLEU transliteration and 87–95% phonetic alignment accuracy across language/script pairs. Includes a case study on preprocessing Moroccan Arabic (Darija) for LLM training.
GenAI for Moroccan Darija: Challenges and Early Results
Conference presentation at the 7th International Congress for Moroccan Arabic, discussing challenges and early results in applying generative AI to Moroccan Darija.
Gherbal v4: Comprehensive Evaluation Report — Language Identification Across 214 Languages
Comprehensive evaluation of Gherbal v4 across 10 models, 8 benchmarks, and 5 scoping regimes. Gherbal v4 achieves 0.836 average accuracy — outperforming OpenLID v2, GlotLID, and NLLB-LID. The report covers Arabic dialect identification, Arabizi detection, African language coverage, and model efficiency analysis.