Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models

Being modeled as a single-label classification task for a long time, recent work has argued that Arabic Dialect Identification (ADI) should be framed as a multi-label classification task. However, ADI remains constrained by the availability of single-label datasets, with no large-scale multi-label resources available for training. By analyzing models trained on single-label ADI data, we show that the main difficulty in repurposing such datasets for Multi-Label Arabic Dialect Identification (MLADI) lies in the selection of negative samples, as many sentences treated as negative could be acceptable in multiple dialects. To address these issues, we construct a multi-label dataset by generating automatic multi-label annotations using GPT-4o and binary dialect acceptability classifiers, with aggregation guided by the Arabic Level of Dialectness (ALDi). Afterward, we train a BERT-based multi-label classifier using curriculum learning strategies aligned with dialectal complexity and label cardinality. On the MLADI leaderboard, our best-performing LahjatBERT model achieves a macro F1 of 0.69, compared to 0.55 for the strongest previously reported system.

Citation

A. Mekky, M. El Zeftawy, L. Hassan, A. Keleg, P. Nakov, "Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models," 2026, pp. 261-274.

Conference

Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects

Keywords

39 Education, 3901 Curriculum and Pedagogy, 46 Information and Computing Sciences, 4611 Machine Learning, 47 Language, Communication and Culture

Source

Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects

Publisher

Association for Computational Linguistics

DOI

10.18653/v1/2026.vardial-1.22

Additional links

https://aclanthology.org/2026.vardial-1.22/