TCE at Qur'an QA 2023 Shared Task: Low Resource Enhanced Transformer-based Ensemble Approach for Qur'anic QA
This work addresses the problem of improving question answering accuracy for the Qur'an in a low-resource setting, representing an incremental advancement in domain-specific NLP.
The paper tackled the challenge of low-resourced training data for Qur'anic question answering by using transfer learning and a voting ensemble with transformer-based models, achieving a MAP score of 25.05% for task A and a pAP of 57.11% for task B.
In this paper, we present our approach to tackle Qur'an QA 2023 shared tasks A and B. To address the challenge of low-resourced training data, we rely on transfer learning together with a voting ensemble to improve prediction stability across multiple runs. Additionally, we employ different architectures and learning mechanisms for a range of Arabic pre-trained transformer-based models for both tasks. To identify unanswerable questions, we propose using a thresholding mechanism. Our top-performing systems greatly surpass the baseline performance on the hidden split, achieving a MAP score of 25.05% for task A and a partial Average Precision (pAP) of 57.11% for task B.