Abstract
This work addresses the challenges of question answering for vintage texts like the Quran. It introduces two tasks: passage retrieval and reading comprehension. For passage retrieval, it employs unsupervised fine-tuning sentence encoders and supervised multi-task learning. In reading comprehension, it fine-tunes an Electra-based model, demonstrating significant improvements over baseline models. Our best AraElectra model achieves 46.1% partial Average Precision (pAP) on the unseen test set, outperforming the baseline by 23%.- Anthology ID:
- 2023.arabicnlp-1.79
- Volume:
- Proceedings of ArabicNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore (Hybrid)
- Editors:
- Hassan Sawaf, Samhaa El-Beltagy, Wajdi Zaghouani, Walid Magdy, Ahmed Abdelali, Nadi Tomeh, Ibrahim Abu Farha, Nizar Habash, Salam Khalifa, Amr Keleg, Hatem Haddad, Imed Zitouni, Khalil Mrini, Rawan Almatham
- Venues:
- ArabicNLP | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 714–719
- Language:
- URL:
- https://aclanthology.org/2023.arabicnlp-1.79
- DOI:
- 10.18653/v1/2023.arabicnlp-1.79
- Cite (ACL):
- Ghazaleh Mahmoudi, Yeganeh Morshedzadeh, and Sauleh Eetemadi. 2023. GYM at Qur’an QA 2023 Shared Task: Multi-Task Transfer Learning for Quranic Passage Retrieval and Question Answering with Large Language Models. In Proceedings of ArabicNLP 2023, pages 714–719, Singapore (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- GYM at Qur’an QA 2023 Shared Task: Multi-Task Transfer Learning for Quranic Passage Retrieval and Question Answering with Large Language Models (Mahmoudi et al., ArabicNLP-WS 2023)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2023.arabicnlp-1.79.pdf