Biomedical Event Extraction (BEE) is a challenging task that involves modeling complex relationships between fine-grained entities in biomedical text. Most existing BEE models rely on classification methods that ignore label semantics and argument dependencies in the data. Although generative models that use prompts are increasingly being used for event extraction, they face two main challenges: creating effective prompts for the biomedical domain and dealing with events with complex structures in the text. To address these limitations, we propose GenBEE, a generative model enhanced with structure-aware prefixes for biomedical event extraction. GenBEE constructs event prompts that leverage knowledge distilled from large language models (LLMs), thereby incorporating both label semantics and argument dependency relationships. Additionally, GenBEE introduces a structural prefix learning module that generates structure-aware prefixes with structural prompts, enriching the generation process with structural features. Extensive experiments on three benchmark datasets demonstrate the effectiveness of GenBEE and it achieves state-of-the-art performance on the MLEE and GE11 datasets. Moreover, our analysis shows that the structural prefixes effectively bridge the gap between structural prompts and the representation space of generative models, enabling better integration of event structural information.

翻译：生物医学事件抽取是一项具有挑战性的任务，涉及对生物医学文本中细粒度实体间的复杂关系进行建模。现有的大多数生物医学事件抽取模型依赖于分类方法，忽略了数据中的标签语义和论元依赖关系。尽管使用提示的生成模型越来越多地用于事件抽取，但它们面临两个主要挑战：为生物医学领域创建有效的提示，以及处理文本中具有复杂结构的事件。为了应对这些局限性，我们提出了GenBEE，一种通过结构感知前缀增强的、用于生物医学事件抽取的生成模型。GenBEE构建的事件提示利用了从大语言模型中提炼的知识，从而融合了标签语义和论元依赖关系。此外，GenBEE引入了一个结构前缀学习模块，该模块通过结构提示生成结构感知前缀，从而用结构特征丰富了生成过程。在三个基准数据集上的大量实验证明了GenBEE的有效性，并在MLEE和GE11数据集上取得了最先进的性能。此外，我们的分析表明，结构前缀有效地弥合了结构提示与生成模型表示空间之间的差距，从而实现了事件结构信息的更好整合。