评测多种模型在葡萄牙语临床实体识别中的表现，发现mmBERT效果最佳。
Clinical named entity recognition in the Portuguese language: a benchmark of modern BERT models and LLMs
- 采用mmBERT等多语言模型处理葡萄牙语临床文本
- mmBERT-base微调后达到0.76的F1分数，最优
- 迭代分层采样有效缓解类别不平衡问题
临床笔记包含宝贵非结构化信息。命名实体识别（NER）可自动提取医学概念，但葡萄牙语相关基准仍稀缺。本研究评估了基于BERT的模型与大语言模型（LLMs）在葡萄牙语临床NER中的表现，并测试缓解多标签不平衡的策略。使用公开的SemClinBr数据集和私有的乳腺癌数据集，在相同训练条件下对比BioBERTpt、BERTimbau、ModernBERT、mmBERT与GPT-5、Gemini-2.5等模型，以精确率、召回率和F1分数为评估指标。探索了迭代分层、加权损失和过采样策略。结果表明，mmBERT-base模型表现最佳（微平均F1=0.76），优于所有其他模型。迭代分层显著改善类别平衡并提升整体性能。多语言BERT模型，尤其是mmBERT，适用于葡萄牙语临床NER，且可在有限算力下本地运行。均衡数据划分策略进一步提升效果。
原文摘要 · Abstract (English)
Clinical notes contain valuable unstructured information. Named entity recognition (NER) enables the automatic extraction of medical concepts; however, benchmarks for Portuguese remain scarce. In this study, we aimed to evaluate BERT-based models and large language models (LLMs) for clinical NER in Portuguese and to test strategies for addressing multilabel imbalance. We compared BioBERTpt, BERTimbau, ModernBERT, and mmBERT with LLMs such as GPT-5 and Gemini-2.5, using the public SemClinBr corpus and a private breast cancer dataset. Models were trained under identical conditions and evaluated using precision, recall, and F1-score. Iterative stratification, weighted loss, and oversampling were explored to mitigate class imbalance. The mmBERT-base model achieved the best performance (micro F1 = 0.76), outperforming all other models. Iterative stratification improved class balance and overall performance. Multilingual BERT models, particularly mmBERT, perform strongly for Portuguese clinical NER and can run locally with limited computational resources. Balanced data-splitting strategies further enhance performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。