Summary of Tce at Qur’an Qa 2023 Shared Task: Low Resource Enhanced Transformer-based Ensemble Approach For Qur’anic Qa, by Mohammed Alaa Elkomy et al.
TCE at Qur’an QA 2023 Shared Task: Low Resource Enhanced Transformer-based Ensemble Approach for Qur’anic QA
by Mohammed Alaa Elkomy, Amany Sarhan
First submitted to arxiv on: 23 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper tackles two Qur’an QA 2023 shared tasks using a novel approach that combines transfer learning with voting ensembles to improve prediction stability. To address the limited training data, the authors employ different architectures and learning mechanisms across multiple Arabic pre-trained transformer-based models. A thresholding mechanism is also proposed for identifying unanswerable questions. The top-performing systems significantly outperform 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. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper finds answers to tricky Quranic questions using special computer models. To make these models work better with little training data, the researchers use a team of different models that vote together on the answer. They also try out different kinds of learning and ask special questions to figure out which ones can’t be answered. The best combination does much better than expected! |
Keywords
* Artificial intelligence * Precision * Transfer learning * Transformer
