--- title: "TranTranUIT at MAHED Shared Task: Multilingual Transformer" description: "The paper addresses Sub-task 1 of the MAHED 2025 Shared Task, which asks systems to label Arabic… 8 references, cited by 1 paper here." authors: ["Trinh Tran Tran", "Thìn \\DJặng Văn"] year: 2025 venue: "Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks" source: "https://aclanthology.org/2025.arabicnlp-sharedtasks.81/" doi: "10.18653/v1/2025.arabicnlp-sharedtasks.81" 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/en/papers/tran-2025-trantranuit-mahed-shared-task-multilingual/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tran-2025-trantranuit-mahed-shared-task-multilingual/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/15/) / TranTranUIT at MAHED Shared Task: Multilingual Transformer Ensemble with Advanced Data Augmentation and Optuna-based Hyperparameter Optimization # TranTranUIT at MAHED Shared Task: Multilingual Transformer Ensemble with Advanced Data Augmentation and Optuna-based Hyperparameter Optimization **Authors:** Trinh Tran Tran and [Thìn \\DJặng Văn](https://md.research.elamur.ai/free/en/authors/thin-djang-van/) · **Year:** 2025 · **Venue:** [Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks](https://md.research.elamur.ai/free/en/venues/arabicnlp/) ([ArabicNLP 2025](https://md.research.elamur.ai/free/en/venues/arabicnlp/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2025.arabicnlp-sharedtasks.81/) · [PDF](https://aclanthology.org/2025.arabicnlp-sharedtasks.81.pdf) · [DOI 10.18653/v1/2025.arabicnlp-sharedtasks.81](https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.81) · [OpenAlex](https://openalex.org/W4416037622) **Citations:** 0 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/tran-2025-trantranuit-mahed-shared-task-multilingual/cited-by/) in our library, of the 149,439 papers whose bibliographies we read ## Summary The paper addresses Sub-task 1 of the MAHED 2025 Shared Task, which asks systems to label Arabic social media posts as hate, hope, or not_applicable. Three things make this hard: diglossia between MSA and regional dialects (Egyptian, Gulf, Levantine, Maghrebi), noisy informal spelling, and skewed labels, with not_applicable making up over half of the 6,890 training posts. The official metric is therefore macro-F1, and dev/test labels are available only through a blind leaderboard. The authors fine-tune three encoders with different pre-training backgrounds: - AraBERTv2, for formal MSA; - AraBERT-Twitter, for informal and dialectal text; - XLM-RoBERTa, for multilingual coverage. Their class probabilities are averaged with equal weights. Training data is expanded by a mix of back-translation (70%) and EDA (30%), and character-level noise is then added. Optuna tunes the main training hyperparameters. The ensemble reaches 0.65 macro-F1 on the test set, compared with 0.61 for the best single model. The authors attribute most of the gain to better recall on the minority hope class. The result is a cheap, simple recipe for noisy, imbalanced, dialect-rich classification. ## Key points - **Training data:** 1,301 hate, 1,892 hope and 3,697 not_applicable posts. The dev set (1,476 posts) and test set (1,477 posts) are evaluated only via leaderboard submissions, and all tuning uses the training set alone. - **Test macro-F1:** AraBERTv2 0.60, AraBERT-Twitter 0.61, XLM-RoBERTa 0.60, uniform soft-voting ensemble 0.65. The authors say the system beats mBERT and Arabic LLaMA-based models but give no numbers for those baselines. - **Augmentation ablation:** no augmentation 0.62, EDA only 0.59, back-translation only 0.60, noise only 0.59, full pipeline 0.65. The prose calls the single methods small gains, but the table shows them below the no-augmentation baseline. - **Pipeline details:** - back-translation chain Arabic→English→French→Arabic; - EDA with synonym replacement, insertion, swap and deletion; - normalization: diacritic removal, Alef unification, elongation stripping, removal of non-Arabic symbols and emojis; - Optuna over 20 trials (learning rate, batch size, weight decay, dropout) with early stopping; - PyTorch 2.2 and HuggingFace Transformers 4.39 on Kaggle P100 GPUs. - **Stated limitations:** no significance testing, back-translation depends on third-party APIs, and the combined augmentation costs more compute than any single method. ## Interesting ideas - Choose ensemble members for the language register each one covers (formal, informal, multilingual), not just for architectural variety, so their errors are less correlated - Averaging probabilities rather than counting votes lets one model's confident prediction for a rare class survive when the other models lean toward the majority class - Character-level noise alone gave nothing; it helped only when applied on top of meaning-preserving and lexical variation - The ablation shows individual augmentations can fall below the no-augmentation baseline while their combination wins, so components must be tested both alone and together - Tuning only on training data and treating the leaderboard as a sealed test keeps reported scores honest under blind conditions ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (learn): pick the silver-data witness parsers so they were trained on different registers (news, web, dialogue), which makes their agreement stronger evidence of a correct tree. - **I2** (tree): combine gparse and perceptron parser scores per arc and label instead of taking majority-vote heads, so rare relations are less likely to be overwritten by frequent ones. - **I3** (tokens): when hardening the tokenizer and tagger against typos, elongations and casing slips, add the noise to already paraphrased sentences rather than to the clean originals only. - **I4** (learn): evaluate each self-induced repair rule or data source both in isolation and in the full mix, always keeping the untouched baseline as a negative control. - **I5** (answer): keep a held-out set of school-course tests and fable QA that is never used for tuning, so reported accuracy reflects real generalization. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Vietnam National University Ho Chi Minh City](https://md.research.elamur.ai/free/en/universities/vietnam-national-university-ho-chi-minh-city/) — University, Ho Chi Minh City, Vietnam · 21 works · 14 citations - [University of Information Technology](https://md.research.elamur.ai/free/en/universities/university-of-information-technology/) — University, Ho Chi Minh City, Vietnam · 13 works · 7 citations 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works 🧭 Topics (2): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works · [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 828 works ## Cite Cite as: Trinh Tran Tran and Thìn \\DJặng Văn. 2025. TranTranUIT at MAHED Shared Task: Multilingual Transformer Ensemble with Advanced Data Augmentation and Optuna-based Hyperparameter Optimization. Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{tran2025trantranuit, title = {{TranTranUIT at MAHED Shared Task: Multilingual Transformer Ensemble with Advanced Data Augmentation and Optuna-based Hyperparameter Optimization}}, author = {Trinh Tran Tran and Thìn DJặng Văn}, booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks}, year = {2025}, doi = {10.18653/v1/2025.arabicnlp-sharedtasks.81}, url = {https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.81} } ``` - [← previous Tracing L1 Interference in English Learner Writing: A Longitudinal Corpus with Error Annotations](https://md.research.elamur.ai/free/en/papers/acharya-2025-tracing-l1-interference-english-learner/) - [next → Uncertainty-driven Partial Diacritization for Arabic Text](https://md.research.elamur.ai/free/en/papers/alblooshi-2025-uncertainty-driven-partial-diacritization-arabic/) - [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/15/) ## References 8 references, 4 of them with a card of ours. ↗ leads to the work. 1. Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, and Masanori Koyama. 2019. [Optuna: A next-generation hyperparameter optimization framework](https://md.research.elamur.ai/free/en/papers/akiba-2019-optuna-next-generation-hyperparameter-optimization/). In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pages 2623–2631. 2. Wissam Antoun, Fady Baly, and Hazem Hajj. 2020. [AraBERT: Transformer-based model for Arabic language understanding](https://md.research.elamur.ai/free/en/papers/antoun-2020-arabert-transformer-based-model-arabic/). In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 9–15, Marseille, France. European Language Resource Association. [↗](https://doi.org/10.48550/arxiv.2003.00104) 3. Markus Bayer, Marc-André Kaufhold, and Christian Reuter. 2022. A survey on data augmentation for text classification. ACM Computing Surveys, 55(7):1–39. [↗](https://doi.org/10.1145/3544558) 4. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8440– 8451, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.acl-main.747) 5. Hercules Dalianis. 2018. Evaluation metrics and evaluation. In Clinical Text Mining: secondary use of electronic patient records, pages 45–53. Springer. [↗](https://doi.org/10.1007/978-3-319-78503-5_6) 6. Kareem Darwish, Nizar Habash, Mourad Abbas, Hend Al-Khalifa, Huseein T Al-Natsheh, Houda Bouamor, Karim Bouzoubaa, Violetta Cavalli-Sforza, Samhaa R El-Beltagy, and Wassim El-Hajj. 2021. A panoramic survey of natural language processing in the arab world. Communications of the ACM, 64(4):72–81. Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6382–6388, Hong Kong, China. Association for Computational Linguistics. [↗](https://doi.org/10.1145/3447735) 7. Wajdi Zaghouani, Md Rafiul Biswas, Mabrouka Bessghaier, Shimaa Ibrahim, Georgios Mikros, Abul Hasnat, and Firoj Alam. 2025. [MAHED shared task: Multimodal detection of hope and hate emotions in arabic content](https://md.research.elamur.ai/free/en/papers/zaghouani-2025-mahed-shared-task-multimodal-detection/). In Proceedings of the Third Arabic Natural Language Processing Conference (Arabic-NLP 2025), Suzhou, China. Association for Computational Linguistics. 8. Wajdi Zaghouani, Hamdy Mubarak, and Md Rafiul Biswas. 2024. [So hateful! building a multi-label hate speech annotated arabic dataset](https://md.research.elamur.ai/free/en/papers/zaghouani-2024-so-hateful-building-multi-label/). In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15044–15055. *Updated 1 November 2026*