There are 1 repository under arabic-dialects topic.
A suite of Arabic natural language processing tools developed by the CAMeL Lab at New York University Abu Dhabi.
The "عربي - Franko" Chrome extension is designed to provide translation services between Franko text and Arabic. It enables users to easily translate text from Franko to Arabic and vice versa.
Fine-tune BERT models to classify Arabic text by different dialects.
Egyptian / Modern Standard Arabic language identification system
domain-independent multi-dialect Arabic stop words
using AraBert to classify different Arabic dialects. ranked fourth in WANLP2020 workshop.
Arabic Dialect Identification between 18 country-level Arabic dialects using QADI dataset and pretrained language model AraBERT
We utilized a pre-trained model to classify Arabic text. After conducting extensive research, we found that MarBERT was the best model for classifying Arabic offensive tweets. It focuses on dialectal Arabic (DA) and Modern Standard Arabic (MSA). The competition involves two shared sub-tasks: detecting whether a tweet is offensive or not; and detecting whether a tweet contains hate speech or not. It detected offensive sentences with 84.9% accuracy and F1-Score of 83.5%, and hate speech with 93.4% accuracy and F1-Score of 80.4%.
A machine learning/deep learning approach to classify the dialect of arabic text.
The codebase for the "ALDi: Quantifying the Arabic Level of Dialectness of Text" paper accepted to EMNLP 2023.
A light stemmer for MDA (Moroccan Dialect Arabic) based on BPE (Byte Pair Encoding) algorithm implemented with Typescript
WIBARAB is a project in the field of Arabic dialectology. It consists of various regional sub-projects (four PhD projects) and a large database about bedouin-type dialects of Arabic. The Feature Database will be the main point of integrating the results of the sub-projects. In this repository we collect the primary data of the database in TEI/XML.
Named Entity Recognition project for Algerian Dialect