--- title: "Curriculum Learning and Pseudo-Labeling Improve — Mekky 2026" description: "Arabic Dialect Identification has usually been treated as assigning one country label per sentence." authors: ["Ali Mekky", "Mohamed El Zeftawy", "Lara Hassan", "Amr Keleg", "Preslav Nakov"] year: 2026 venue: "Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects" source: "https://aclanthology.org/2026.vardial-1.22/" doi: "10.18653/v1/2026.vardial-1.22" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/papers/mekky-2026-curriculum-learning-pseudo-labeling-improve/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/mekky-2026-curriculum-learning-pseudo-labeling-improve/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2026](https://md.research.elamur.ai/free/papers/2026/page/2/) / Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models # Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models **Authors:** Ali Mekky, Mohamed El Zeftawy, Lara Hassan, Amr Keleg, [Preslav Nakov](https://md.research.elamur.ai/free/authors/preslav-nakov/) · **Year:** 2026 · **Venue:** Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.vardial-1.22/) · [PDF](https://aclanthology.org/2026.vardial-1.22.pdf) · [DOI 10.18653/v1/2026.vardial-1.22](https://doi.org/10.18653/v1/2026.vardial-1.22) · [OpenAlex](https://openalex.org/W7140124422) **Citations:** 0 citations (openalex-snapshot · 2026-10-14) ## Summary Arabic Dialect Identification has usually been treated as assigning one country label per sentence. In reality, many utterances sound natural in several dialects. The multi-label variant (MLADI) still has no large multi-label training resource: only small evaluation sets carry multiple labels. The authors trained binary dialect acceptability classifiers on single-label NADI 2020, 2021 and 2023 data and analyzed their training dynamics. This showed that the core obstacle is negative sampling: many tweets from other countries labeled as negatives are actually acceptable in the target dialect. To address this, they built a pseudo-labeled multi-label training set. It merges GPT-4o annotations with predictions from 18 binary classifiers, and the merging rule depends on each sentence's ALDi score. On this data they trained LahjatBERT, a BERT-based multi-label model, with and without curriculum learning (ordered by ALDi or by label cardinality). The ALDi-curriculum model reaches about 0.69 macro F1 on the MLADI leaderboard, compared with 0.55 for the best earlier system. This shows that single-label corpora can be turned into useful multi-label supervision. ## Key points - **Training data:** NADI 2020, 2021 and 2023 tweets, geo-labeled for 18 countries. Evaluation used the MLADI development set (120 sentences, 8 dialects) and test set (1,000 sentences, 11 dialects). - **Diagnosing label noise:** Training dynamics, following Swayamdipta et al., revealed that a substantial share of "negative" samples are acceptable to native speakers. Flagged cases still need manual checking. - **Hybrid pseudo-labels:** The binary classifiers' conservative predictions are used at the low and high ends of the ALDi scale. GPT-4o's richer labels are used in the mid-range. - **Test-set macro F1:** - LahjatBERT + ALDi curriculum: 69.0 (best) - LahjatBERT without curriculum: 68.0 - Aya-32B: 54.5 - Elyadata (top NADI2024 system): 52.4 - NADI 2024 baseline: 47.0 - **Curriculum trade-off:** Both curricula increase recall at some cost to precision; the cardinality curriculum reaches 81.0 recall on test. Only tweet IDs and derived labels are released. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{mekky2026curriculum, title = {{Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models}}, author = {Mekky, Ali and Zeftawy, Mohamed El and Hassan, Lara and Keleg, Amr and Nakov, Preslav}, booktitle = {Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects}, year = {2026}, doi = {10.18653/v1/2026.vardial-1.22}, url = {https://doi.org/10.18653/v1/2026.vardial-1.22} } ``` - [← previous Culture-Aware Machine Translation in Large Language Models: Benchmarking and Investigation](https://md.research.elamur.ai/free/papers/yuan-2026-culture-aware-machine-translation-large/) - [next → DAMETA: An LLM Benchmark for Danish Metaphor Interpretation with Systematically Varied Distractors](https://md.research.elamur.ai/free/papers/schneidermann-2026-dameta-llm-benchmark-danish-metaphor/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/papers/2026/page/2/) ## References 3 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Ahmed Abdelali, Hamdy Mubarak, Younes Samih, Sabit Hassan, and Kareem Darwish. 2021. QADI: Arabic dialect identification in the wild. In Proceedings of the Sixth Arabic Natural Language Processing Workshop, pages 1–10, Kyiv, Ukraine (Virtual). Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ahmed+Abdelali%2C+Hamdy+Mubarak%2C+Younes+Samih%2C+Sabit+Hassan%2C+and+Kareem+Darwish%2E+2021%2E+QADI%3A+Arabic+dialect+identification+in+the+wild%2E+In+Proceedings+of+the+Sixth+Arabic+Natural+Language+Processing+Wor) 2. Muhammad Abdul-Mageed, AbdelRahim Elmadany, Chiyu Zhang, El Moatez Billah Nagoudi, Houda Bouamor, and Nizar Habash. 2023. NADI 2023: The fourth nuanced Arabic dialect identification shared task. In Proceedings of ArabicNLP 2023, pages 600– 613, Singapore (Hybrid). Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Muhammad+Abdul%2DMageed%2C+AbdelRahim+Elmadany%2C+Chiyu+Zhang%2C+El+Moatez+Billah+Nagoudi%2C+Houda+Bouamor%2C+and+Nizar+Habash%2E+2023%2E+NADI+2023%3A+The+fourth+nuanced+Arabic+dialect+identification+shared+task%2E+In+Pr) 3. Muhammad Abdul-Mageed, AbdelRahim Elmadany, et al. 2021a. Arbert & marbert: Deep bidirectional transformers for arabic. In Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (volume 1: long papers), pages 7088–7105. [↗](https://doi.org/10.48550/arxiv.2101.01785) [our card](https://md.research.elamur.ai/free/papers/abdul-2021-mageed-arbert-marbert-deep-bidirectional-transformers/)