In-Context Meta-Learning vs. Semantic Score-Based Similarity: A Comparative Study in Arabic Short Answer Grading

Menna Fateen, Tsunenori Mine


Abstract
Delegating short answer grading to automated systems enhances efficiency, giving teachers more time for vital human-centered aspects of education. Studies in automatic short answer grading (ASAG) approach the problem from instance-based or reference-based perspectives. Recent studies have favored instance-based methods, but they demand substantial data for training, which is often scarce in classroom settings. This study compares both approaches using an Arabic ASAG dataset. We employ in-context meta-learning for instance-based and semantic score-based similarity for reference-based grading. Results show both methods outperform a baseline and occasionally even surpass human raters when grading unseen answers. Notably, the semantic score-based similarity approach excels in zero-shot settings, outperforming in-context meta-learning. Our work contributes insights to Arabic ASAG and introduces a prompt category classification model, leveraging GPT3.5 to augment Arabic data for improved performance.
Anthology ID:
2023.arabicnlp-1.28
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:
350–358
Language:
URL:
https://aclanthology.org/2023.arabicnlp-1.28
DOI:
10.18653/v1/2023.arabicnlp-1.28
Bibkey:
Cite (ACL):
Menna Fateen and Tsunenori Mine. 2023. In-Context Meta-Learning vs. Semantic Score-Based Similarity: A Comparative Study in Arabic Short Answer Grading. In Proceedings of ArabicNLP 2023, pages 350–358, Singapore (Hybrid). Association for Computational Linguistics.
Cite (Informal):
In-Context Meta-Learning vs. Semantic Score-Based Similarity: A Comparative Study in Arabic Short Answer Grading (Fateen & Mine, ArabicNLP-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.arabicnlp-1.28.pdf