HananeNourMoussa/darija-ner

A repo for NER in the Moroccan dialect using a deep learning approach. # darija-ner Please cite these papers if you use our dataset or models: [1] Hanane Nour Moussa, Asmaa Mourhir, DarNERcorp: An annotated named entity recognition dataset in the Moroccan dialect, Data in Brief, Volume 48, 2023, 109234, ISSN 2352-3409, doi.org. [2] H. N. Moussa and A. Mourhir, "Named Entity Recognition in the Moroccan Dialect," 2023 7th IEEE Congress on Information Science and Technology (CiSt), Agadir - Essaouira, Morocco, 2023, pp. 282-286, doi: 10.1109/CiSt56084.2023.10409973. ## Data_Curation: This folder contains the code referred to in [1]. For more details about the data collection, refer to our paper: doi.org. Our dataset can be found Digital Commons Data: data.mendeley.com ## Training: This folder contains the code of the model training referred to in [2]. ## Models: This folder contains links to download the best performing models. ### Bonus! A demo of our model is hosted on huggingface! huggingface.co