Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

abdelhaqueidali/Moroccan-Arabic-Latin-Orthography

Domaine:

natural language processing
Créateur:
abd
Hôte:
An Amazigh-Inspired Latin Orthography for Moroccan Arabic # Moroccan-Arabic-Latin-Orthography A Latin Orthography for Moroccan Arabic, A better solution for Arabizi. # Check Here * Edit: I came lately across this paper which applies the same approach of adopting Amazigh conventions, You can Read it here # * **Full Orthography: Constantly updated** [README.md], **Read below** ⬇️ * **This orthography Brief Version:** brief.md * There is this version as the following in this orthography which uses the short vowel Shwa "e" and hyphens. A more simplified version is simply, attach words where a hyphen exists, and drop short vowels if not needed, this can be for convenience where not well written form is needed, example: * **Dert-u bac nettɛellem Nnegliziya, ɛend-i imtiḥan** * **Drtu bac nttɛllm Nngliziya, ɛndi imtiḥan** * This can decrease the friction in using this system. * Short vowel can be kept though: * **Dertu bac nettɛellem Nnegliziya, ɛendi imtiḥan** --- # A Latin Orthography for Moroccan Arabic (Darija) This repository presents a version of Latin-script orthography for Moroccan Arabic (Darija), adapted directly from the established Amazigh-Latin system to resolve the issues in conventional Darija writings. Rather than inventing new symbols or reassigning new letters, this approach leverages an established alphabet already integrated into modern smartphone and desktop keyboards. By aligning with this system, it directly benefits from existing input methods, and character sets. ## Scope & Intent * **Framework First:** This establishes the core orthographic rules (graphemes, word boundaries, and clitics). * **Open for Improvement:** While functional and ready for use, this system remains open to feedback and refinement. --- # ​A Latin Orthography for Moroccan Arabic (Amazigh Model) ## Introduction Writing Moroccan Arabic (referred to as Darija) in the Arabic script remains the default orthography, accounting for the majority of written usage. It relies on the well-established conventions of Standard Arabic and …

Visit

github.com

Tasks

text normalization

Languages

AmazighArabic, Algerian SpokenArabic, Moroccan SpokenBerber

Similaires

abdelhaqueidali/Tashelhit-Tifinagh-Latin-Parallel-Tatoeba-Datasetabdelhaqueidali/Kabyle-Latin-to-Tifinagh-Parallel-CorpusEmoji-Aware Sentiment Analysis for Moroccan Darija in Arabic and Latin ScriptsMANorm: A Normalization Dictionary for Moroccan Arabic Dialect Written in Latin Scriptabdelhaqueidali/Tawalt-Amazigh-Arabic-DictionaryArabic, Tunisian Spoken Orthography

abdelhaqueidali/Tashelhit-Tifinagh-Latin-Parallel-Tatoeba-Dataset

This dataset provides a parallel corpus of the Tachelhit language ($\text{Tacelḥit}$ / $\text{Tamazi

abdelhaqueidali/Kabyle-Latin-to-Tifinagh-Parallel-Corpus

This dataset provides a parallel corpus of the Kabyle language (Taqbaylit), pairing native Latin-bas

Emoji-Aware Sentiment Analysis for Moroccan Darija in Arabic and Latin Scripts

MANorm: A Normalization Dictionary for Moroccan Arabic Dialect Written in Latin Script

Social media user-generated text is actually the main resource for many NLP tasks. This text however

abdelhaqueidali/Tawalt-Amazigh-Arabic-Dictionary

Arabic, Tunisian Spoken Orthography