---
language: 
- ar
- en
license: apache-2.0
datasets:
- 4Dialects
- MADAR
- CSCS
thumbnail: https://www.informatik.hu-berlin.de/en/forschung-en/gebiete/ml-en/resolveuid/a6f82e0d7fa446a59c902cac4cafa9cb/@@images/image/preview
tags:
- flair
- PoS-Tagging
- sequence labeling
- Token Classification
- Dialectal Arabic
- Code-Switching
- Code-mixing
metrics:
- f1
widget:
- text: "لائحة «الوطنية للصحافة».. خطوة جديدة في طريق «الحصار»"
---


# Arabic Flair + fastText Part-of-Speech tagging Model (Egyptian and Levant)
Pretrained Part-of-Speech tagging model built on a joint corpus written in Egyptian and Levantine (Jordanian, Lebanese, Palestinian, Syrian) dialects with code-switching of Egyptian Arabic and English. The model is trained using [Flair](https://aclanthology.org/C18-1139/) (forward+backward)and [fastText](https://fasttext.cc) embeddings.



# Pretraining Corpora:
This sequence labeling model was pretrained on three corpora jointly:
1. [4 Dialects](https://huggingface.co/datasets/viewer/?dataset=arabic_pos_dialect)
A Dialectal Arabic Datasets containing four dialects of Arabic, Egyptian (EGY), Levantine (LEV), Gulf (GLF), and Maghrebi (MGR). Each dataset consists of a set of 350 manually segmented and PoS tagged tweets.
2. [UD South Levantine Arabic MADAR](https://universaldependencies.org/treebanks/ajp_madar/index.html)
A Dataset with 100 manually-annotated sentences taken from the [MADAR](https://camel.abudhabi.nyu.edu/madar/) (Multi-Arabic Dialect Applications and Resources) project by [Shorouq Zahra](mailto:shorouqjzahra@gmail.com).
3. Parts of the Cairo Students Code-Switch (CSCS) corpus developed for ["Collection and Analysis of Code-switch Egyptian Arabic-English Speech Corpus"](https://aclanthology.org/L18-1601.pdf) by Hamed et al.

# Usage

# Example

# Citation
*if you use this model in your work, please consider citing this work:*
```latex
@unpublished{MMHU21
author = "M. Megahed and A. Akbik",
title = "Sequence Labeling Architectures in Diglossia",
note = "In preparation",
}
```