Cross-Language Approach for Quranic QA

2025-01-29

AI Summary

This work addresses the language gap between Classical Arabic Qur’anic verses and Modern Standard Arabic queries, along with the low-resource bottleneck in cross-lingual Qur’an question answering. Methodologically, we propose the first solution integrating English translation-based data augmentation with multi-model cross-lingual fine-tuning. Our approach employs a preprocessing pipeline comprising machine translation, question rewriting, and English-answer retrieval, followed by cross-lingual transfer and few-shot fine-tuning across seven state-of-the-art models—including RoBERTa-Base and DeBERTa-v3-Base. Experimental results show that RoBERTa-Base achieves MAP@10 = 0.34 and MRR = 0.52, while DeBERTa-v3-Base attains Recall@10 = 0.50 and Precision@10 = 0.24—substantially outperforming monolingual baselines. This work establishes a reusable, low-resource adaptation paradigm for cross-lingual QA over religious texts.

Technology Category

• Natural Language Processing: Question Answering
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Question answering systems face critical limitations in languages with limited resources and scarce data, making the development of robust models especially challenging. The Quranic QA system holds significant importance as it facilitates a deeper understanding of the Quran, a Holy text for over a billion people worldwide. However, these systems face unique challenges, including the linguistic disparity between questions written in Modern Standard Arabic and answers found in Quranic verses written in Classical Arabic, and the small size of existing datasets, which further restricts model performance. To address these challenges, we adopt a cross-language approach by (1) Dataset Augmentation: expanding and enriching the dataset through machine translation to convert Arabic questions into English, paraphrasing questions to create linguistic diversity, and retrieving answers from an English translation of the Quran to align with multilingual training requirements; and (2) Language Model Fine-Tuning: utilizing pre-trained models such as BERT-Medium, RoBERTa-Base, DeBERTa-v3-Base, ELECTRA-Large, Flan-T5, Bloom, and Falcon to address the specific requirements of Quranic QA. Experimental results demonstrate that this cross-language approach significantly improves model performance, with RoBERTa-Base achieving the highest MAP@10 (0.34) and MRR (0.52), while DeBERTa-v3-Base excels in Recall@10 (0.50) and Precision@10 (0.24). These findings underscore the effectiveness of cross-language strategies in overcoming linguistic barriers and advancing Quranic QA systems

Problem

• Quranic Question Answering
• Language Disparity
• Data Scarcity

Innovation

• Cross-lingual Approach
• Data Augmentation
• Pre-trained Language Models