araelectra-base-discriminator-tydi-tafseer-pairs

Quran Passage Retrieval Model

This is a fine-tuned model on Arabic passage retrieval datasets, used for Quran QA 2023 Task A.

Model Description

This model was fine-tuned to perform text classification on an Arabic dataset. The task involves identifying relevant passages from the Quran in response to specific questions, focusing on retrieval quality.

Base model: Pretrained transformer-based model (e.g., AraBERT, CAMeLBERT, AraELECTRA).
Task: Passage retrieval (text classification).
Dataset: Fine-tuned on the Quran QA 2023 dataset.

Intended Use

Language: Arabic
Task: Passage retrieval for Quran QA
Usage: Use this model for ranking and retrieving relevant passages from a corpus of Arabic text, primarily for question answering tasks.

Evaluation Results

reported in the paper

How to Use

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained("mohammed-elkomy/quran-qa")
tokenizer = AutoTokenizer.from_pretrained("mohammed-elkomy/quran-qa")

inputs = tokenizer("Your input text", return_tensors="pt")
outputs = model(**inputs)

## Citation
    If you use this model, please cite the following:

@inproceedings{elkomy2023quran, title={TCE at Qur’an QA 2023 Shared Task: Low Resource Enhanced Transformer-based Ensemble Approach for Qur’anic QA}, author={Mohammed ElKomy and Amany Sarhan}, year={2023}, url={https://github.com/mohammed-elkomy/quran-qa/}, }

@inproceedings{elkomy2022quran, title={TCE at Qur'an QA 2022: Arabic Language Question Answering Over Holy Qur'an Using a Post-Processed Ensemble of BERT-based Models}, author={Mohammed ElKomy and Amany Sarhan}, year={2022}, url={https://github.com/mohammed-elkomy/quran-qa/}, }