SHU at AdabEval 2026: Category-Aware Fine-Tuning of MARBERT for Arabic Politeness and Pragmatic Function Classification

Alla Zwawi, Stephen Wu


Abstract
This paper describes our submission to the AdabEval 2026 shared task, addressing Subtask A (politeness classification) and Subtask B (multi-label pragmatic category prediction). For Subtask A, we fine-tuned MARBERT using weighted cross-entropy to mitigate class imbalance. For Subtask B, we apply BCEWithLogitsloss with inverse-frequency positive weighting to address the minority categories, and we introduce a category merging strategy to reduce categories’ sparsity and annotation variation. Finally, we propose a stacked architecture where predicted pragmatic categories are injected as auxiliary features into the politeness classifier. Our results demonstrate that dialect-aware modelling, class-imbalance handling, and category-aware stacking improve Macro-F1 across both subtasks, achieving 0.85 for Subtask A and 0.55 for Subtask B on the test set.
Anthology ID:
2026.osact-1.20
Volume:
The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Hend Al-Khalifa, Mo El-Haj, Saad Ezzini
Venues:
OSACT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
174–178
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-osact-20
DOI:
10.63317/5csq27bytjtc
Bibkey:
Cite (ACL):
Alla Zwawi and Stephen Wu. 2026. SHU at AdabEval 2026: Category-Aware Fine-Tuning of MARBERT for Arabic Politeness and Pragmatic Function Classification. In The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks, pages 174–178, Palma, Mallorca (Spain). Association for Computational Linguistics.
Cite (Informal):
SHU at AdabEval 2026: Category-Aware Fine-Tuning of MARBERT for Arabic Politeness and Pragmatic Function Classification (Zwawi & Wu, OSACT 2026)
Copy Citation: