Pre-trained Transformers for Arabic Language Understanding and Generation (Arabic BERT, Arabic GPT2, Arabic ELECTRA)

Fine-tune BERT models to classify Arabic text by different dialects.

Arabic Dialect Identification between 18 country-level Arabic dialects using QADI dataset and pretrained language model AraBERT

Arabic_Dialect_Identification_NLP-AIM-Task

After collecting 40 thousand tweets and preprocessing it, I used word embeddings with arabert and tf-idf along with two neural network architectures and 5 machine learning algorithms. Due to the huge size of the dataset, I chose Amazon SageMaker to train the models

Arabic Dialect Sentimenal Analysis

Simple Script to undo Farasa Segmentation, compatible with AraBERT pre-segmentation

Easy to use extractive text summarization with AraBERT

Mental health diagnosis tool using NLP and ML for Arabic inputs, with a Laravel web application interface

Diacritics are short vowels with a constant length that are spoken. The same word in the Arabic language can have different meanings and different pronunciations based on how it is diacritized. In this project, we implement a pipeline to predict the diacritic of each character in an Arabic text using Natural Language Processing techniques.

This is an experiment for Qur'an QA for the shared task at the OSCAT workshop

A web-based intelligent system designed to classify and manage student inquiries at the university. Students can submit questions related to Finance, Student Affairs, IT, or Exams, and the system automatically routes each inquiry to the appropriate department.

This project focuses on developing a sentiment analysis model for Arabic text, leveraging hybrid transformer-based models (AraBERT) and LSTM approaches.

Emotion Prediction in Arabic Text

Many countries speak Arabic; however, each country has its own dialect, the aim of this project is to build a model that predicts the dialect given the text.

an AI powered Arabic Question Answering system built by fine tuning the AraBERT model on the Arabic SQuAD dataset. , Developed as part of the ZakyBootcamp AI track

Dialectical Arabic Sentiment Analysis

Disambiguation Study for Arabic Applied on Text Classification

A Named Entity Recognition model for Arabic political texts using AraBERT