用词典后处理提升生物医学命名实体识别，但泛化能力受限。
Enhancing Biomedical Named Entity Recognition using GLiNER-BioMed with Targeted Dictionary-Based Post-processing for BioASQ 2025 task 6
- 基于词典的后处理策略修正模型误判
- 开发集上微F1从0.79提至0.83，测试集反降至0.77
- 适合关注模型泛化与实体细粒度区分的研究者
生物医学命名实体识别（BioNER）是大规模生物医学语义索引与问答挑战（BioASQ）任务6的核心任务，对从科学文献中提取信息至关重要，但常面临基因与化学物质等相似实体类型难以区分的问题。本研究在BioASQ数据集上评估GLiNER-BioMed模型，并引入针对性的词典后处理策略以解决常见误分类。该方法在开发集上显著提升性能，微F1从0.79增至0.83，但在盲测集上表现反而下降，后处理模型微F1为0.77，低于基线0.79。研究还探讨了条件随机场等替代方法的可行性。结果表明，词典精修虽有潜力，但易过拟合开发数据，严重影响实际应用中的泛化能力。
原文摘要 · Abstract (English)
Biomedical Named Entity Recognition (BioNER), task6 in BioASQ (A challenge in large-scale biomedical semantic indexing and question answering), is crucial for extracting information from scientific literature but faces hurdles such as distinguishing between similar entity types like genes and chemicals. This study evaluates the GLiNER-BioMed model on a BioASQ dataset and introduces a targeted dictionary-based post-processing strategy to address common misclassifications. While this post-processing approach demonstrated notable improvement on our development set, increasing the micro F1-score from a baseline of 0.79 to 0.83, this enhancement did not generalize to the blind test set, where the post-processed model achieved a micro F1-score of 0.77 compared to the baselines 0.79. We also discuss insights gained from exploring alternative methodologies, including Conditional Random Fields. This work highlights the potential of dictionary-based refinement for pre-trained BioNER models but underscores the critical challenge of overfitting to development data and the necessity of ensuring robust generalization for real-world applicability.
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。