Arabic_Dialect_Identification_NLP-AIM-Task

Arabic has a widely varying collection of dialects. Many of these dialects remain under-studied due to the rarity of resources.

The goal of AIM task is to classifying the dialect of the tweet writer given the tweet itself.

I used two approches:

1- Machine Learning Aproach Using LinearSVC

2- Deep Learning Approach Using AraBERT Transformer

Deep Learning AraBERT Fine Tuning:

I fine tuned AraBERTv0.2-Twitter base/large you found in this link and the models weights in this drive link

To use AraBERT Models go to the NoteBook Folder or This CoLab Link

---

The Deployment is by Machine learning model and steps to run the flask

1- Download the pkl model from the drive in this link

2- Put the Model in the Flask_Deployment Folder

3- From CMD flask run

---

Deployment

-------------------------------------------------------------------------------------------