TCE at Qur'an QA 2023 Shared Task: Low Resource Enhanced Transformer-based Ensemble Approach for Qur'anic QA
Domaine:
natural language processingType de record:
paper
Créateur:
ElkSar
Hôte:
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.
Similaires
RAG Based QA for Low Resource LanguagesFrancklin9999/low-resource-qa-representationBleztam/Multilingual-QA-Chatbot-for-Low-Resource-LanguagesHealth QA in Low-Resource African LanguagesBhattacharya_Lab at SemEval-2023 Task 12: A Transformer-based Language Model for Sentiment Classification for Low Resource African Languages: Nigerian Pidgin and YorubaCARLOS-hub-droid/qa-rag-low-resource-languages