--- title: "SINAI at #SMM4H–HeaRD 2026 — paper by Piñar et al. (2026)" description: "The SINAI team (Universidad de Jaén) developed an entry for MultiClinAI, one of the shared tasks hosted at SMM4H-HeaRD… 2 references." authors: ["Lucas Molino Piñar", "Manuel Carlos Diaz-Galiano", "María-Teresa Martín-Valdivia"] year: 2026 venue: "Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks" source: "https://aclanthology.org/2026.smm4h-1.4/" doi: "10.18653/v1/2026.smm4h-1.4" 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/pinar-2026-sinai-smm4h-heard-2026-multilingual/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/pinar-2026-sinai-smm4h-heard-2026-multilingual/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/43/) / SINAI at #SMM4H–HeaRD 2026: Multilingual Clinical NER with MrBERT-biomed and Optuna Hyperparameter Optimization # SINAI at #SMM4H–HeaRD 2026: Multilingual Clinical NER with MrBERT-biomed and Optuna Hyperparameter Optimization **Authors:** [Lucas Molino Piñar](https://md.research.elamur.ai/free/en/authors/lucas-molino-pinar/), [Manuel Carlos Diaz-Galiano](https://md.research.elamur.ai/free/en/authors/manuel-carlos-diaz-galiano/) and [María-Teresa Martín-Valdivia](https://md.research.elamur.ai/free/en/authors/maria-teresa-martin-valdivia/) · **Year:** 2026 · **Venue:** [Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks](https://md.research.elamur.ai/free/en/venues/smm4h/) ([Social Media Mining for Health Research and Applications Workshop and Shared Tasks 2026](https://md.research.elamur.ai/free/en/venues/smm4h/2026/)) · **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/2026.smm4h-1.4/) · [PDF](https://aclanthology.org/2026.smm4h-1.4.pdf) · [DOI 10.18653/v1/2026.smm4h-1.4](https://doi.org/10.18653/v1/2026.smm4h-1.4) · [OpenAlex](https://openalex.org/W7166885071) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary The SINAI team (Universidad de Jaén) developed an entry for MultiClinAI, one of the shared tasks hosted at SMM4H-HeaRD 2026. The task is clinical NER for DISEASE, PROCEDURE and SYMPTOM mentions, scored on Spanish texts with strict span-level micro-F1. The MultiClinNER corpus provides annotated clinical documents in seven European languages. The team used all seven for training and kept Spanish for validation and testing. The system has three main parts: - **Separate models per entity type.** They fine-tuned three BIO taggers from MrBERT-biomed, a ModernBERT-based encoder that BSC-LT further pre-trained on biomedical literature. - **Automatic tuning.** Optuna selected the hyperparameters for each model. - **Boundary correction.** A rule-based step adjusts predicted spans to full words, so that subword tokenization does not cost points under strict matching. In development, biomedical pre-training and multilingual data each helped, and they worked best together. On the official test set the system reached F1 of 0.745 (DISEASE), 0.711 (PROCEDURE) and 0.660 (SYMPTOM). Recall dropped sharply on natively written clinical notes compared with translated ones. This suggests that real clinical writing style is a key remaining obstacle. ## Key points - **Encoder:** MrBERT-biomed was created from MrBERT-es by continued pre-training on about 24B biomedical tokens, mostly English (84.7%) and Spanish (14.8%). Its context window is 8,192 tokens. - **Hyperparameter search:** Optuna ran 20 trials per entity model with a TPE sampler and a median pruner. The search covered learning rate, weight decay, warmup, batch size, epochs and gradient accumulation. The selected learning rates ranged from 2.4e-4 to 4.9e-4. - **Development results:** On the Spanish validation set, MrBERT-biomed trained on multilingual data scored best for DISEASE (0.7478) and SYMPTOM (0.7345). For PROCEDURE it scored 0.7597, slightly below MrBERT-es (0.7625). Training on Spanish only was the weakest setup. - **Native-text gap:** On the test set's Native subcorpus, recall fell to 0.501 for PROCEDURE and 0.505 for SYMPTOM. The authors attribute this to abbreviations, idiomatic phrasing and jargon. - **Training and post-processing details:** Training used HuggingFace Transformers on a single 40 GB Ampere GPU with BF16, 512-token windows and a stride of 128. The word-boundary rule is built for Spanish orthography and would need changes for other languages. *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 - [Universidad de Jaén](https://md.research.elamur.ai/free/en/universities/universidad-de-jaen/) — University, Jaén, Spain · 8 works · 1,671 citations 📚 Shelves (6): [🖥️ 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 · [🧬 Biochemistry, Genetics and Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/) · 234 works · [🧬 Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/molecular-biology/) · 231 works 🧭 Topics (2): [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 828 works · [🏷️ Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) · 200 works ## Cite Cite as: Lucas Molino Piñar, Manuel Carlos Diaz-Galiano and María-Teresa Martín-Valdivia. 2026. SINAI at #SMM4H–HeaRD 2026: Multilingual Clinical NER with MrBERT-biomed and Optuna Hyperparameter Optimization. Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{pinar2026sinai, title = {{SINAI at \#SMM4H–HeaRD 2026: Multilingual Clinical NER with MrBERT-biomed and Optuna Hyperparameter Optimization}}, author = {Lucas Molino Piñar, Manuel Carlos Diaz-Galiano and María-Teresa Martín-Valdivia}, booktitle = {Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks}, year = {2026}, doi = {10.18653/v1/2026.smm4h-1.4}, url = {https://doi.org/10.18653/v1/2026.smm4h-1.4} } ``` - [← previous Simultaneous Speech-to-Text Translation Web Application for Estonian](https://md.research.elamur.ai/free/en/papers/podziubanchuk-2026-simultaneous-speech-text-translation-web/) - [next → SiniticMTError: A Machine Translation Dataset with Error Annotations for Sinitic Languages](https://md.research.elamur.ai/free/en/papers/liu-2026-siniticmterror-machine-translation-dataset-error/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/43/) ## References 2 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 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. Salvador Lima-López, Fernando Gallego, and 1 others. 2026a. Overview of the MultiClinAI Shared Task at SMM4H-HeaRD 2026. In Proceedings of the 11th Social Media Mining for Health (\#SMM4H) and Health Real-World Data (HeaRD) Workshop and Shared Tasks. Association for Computational Linguistics. \#\# Limi… [find](https://scholar.google.com/scholar?q=Salvador+Lima%2DL%C3%B3pez%2C+Fernando+Gallego%2C+and+1+others%2E+2026a%2E+Overview+of+the+MultiClinAI+Shared+Task+at+SMM4H%2DHeaRD+2026%2E+In+Proceedings+of+the+11th+Social+Media+Mining+for+Health+%28%5C%23SMM4H%29+and+Health+) *Updated 1 November 2026*