arabert-finetuned-caner

<h1 align="center">arabert-finetuned-caner</h1> <p align="center">An ongoing project for implementation of NLP methods in the field of islamic studies.</p>

Named Entity Recognition

briefly:

• We had to prepair CANERCorpus dataset which is avialable at huggingface. The dataset was not in the BIO format so model couldn't learn anything from it. We used an html version of dataset available on github and extracted a HuggingFace format dataset from it with BIO tags.
• Fine tunning started from a pre-traind model named "bert-base-arabertv02" and after 3 epoch of training model on the above mentioned dataset (80% splitted to training data and 20% to validation data), reached the following results: (evaluation is done by using compute metrics of python evaluate module. note that precision is overall precision, recall is overall recall and so on.)

• Trained model is available at huggingface and you can use it with the following code snippet:

!pip install transformers
from transformers import pipeline
model_checkpoint = "Montazer/arabert-finetuned-caner"
# Replace this with above latest checkpoint
token_classifier = pipeline(
    "token-classification", model=model_checkpoint, aggregation_strategy="simple"
)
s = "حَدَّثَنَا عَبْد اللَّهِ، حَدَّثَنِي عُبَيْدُ اللَّهِ بْنُ عُمَرَ الْقَوَارِيرِيُّ، حَدَّثَنَا يُونُسُ بْنُ أَرْقَمَ، حَدَّثَنَا يَزِيدُ بْنُ أَبِي زِيَادٍ، عَنْ عَبْدِ الرَّحْمَنِ بْنِ أَبِي لَيْلَى، قَالَ شَهِدْتُ عَلِيًّا رَضِيَ اللَّهُ عَنْهُ فِي الرَّحَبَةِ يَنْشُدُ النَّاسَ أَنْشُدُ اللَّهَ مَنْ سَمِعَ رَسُولَ اللَّهِ صَلَّى اللَّهُ عَلَيْهِ وَسَلَّمَ يَقُولُ يَوْمَ غَدِيرِ خُمٍّ مَنْ كُنْتُ مَوْلَاهُ فَعَلِيٌّ مَوْلَاهُ لَمَّا قَامَ فَشَهِدَ قَالَ عَبْدُ الرَّحْمَنِ فَقَامَ اثْنَا عَشَرَ بَدْرِيًّا كَأَنِّي أَنْظُرُ إِلَى أَحَدِهِمْ فَقَالُوا نَشْهَدُ أَنَّا سَمِعْنَا رَسُولَ اللَّهِ صَلَّى اللَّهُ عَلَيْهِ وَسَلَّمَ يَقُولُ يَوْمَ غَدِيرِ خُمٍّ أَلَسْتُ أَوْلَى بِالْمُؤْمِنِينَ مِنْ أَنْفُسِهِمْ وَأَزْوَاجِي أُمَّهَاتُهُمْ فَقُلْنَا بَلَى يَا رَسُولَ اللَّهِ قَالَ فَمَنْ كُنْتُ مَوْلَاهُ فَعَلِيٌّ مَوْلَاهُ اللَّهُمَّ وَالِ مَنْ وَالَاهُ وَعَادِ مَنْ عَادَاهُ"
token_classifier(s)

• This model is deployed on a Huggingface space using Gradio. So you can use it online here!