发表机构
German Research Center for Artificial Intelligence; Carl von Ossietzky University of Oldenburg（德国人工智能研究中心; 奥尔登堡卡尔·冯·奥西茨基大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对跨领域事件抽取难题，提出带显式任务与领域条件的多领域多任务生成框架，通过结合领域条件信号与任务提示实现动态适配，在基准测试中取得了竞争力的性能与跨领域泛化能力。
AI 中文摘要
事件抽取旨在识别事件触发词、分类事件类型并抽取论元，以构建结构化的事件表示。尽管模型在领域内表现强劲，但由于上下文表达和事件模式的差异，开发能跨领域稳健泛化的模型仍具挑战性。现有统一及多任务方法提升了领域内准确率，但应用于未见过的领域时灵活性有限；即便在推理时提供完整事件本体的基于大语言模型的方法，也常比更小的、针对特定任务微调的模型表现更差。我们提出一种统一的多领域多任务训练框架，在单一模型中建模异构事件模式。该方法引入领域条件信号，与特定任务提示结合，无需在推理时提供完整事件标签集即可动态适配特定数据集的模式。该框架支持流水线和端到端抽取设置，促进高效的任务级和领域级迁移。在不同事件抽取基准上的实验表明，我们的方法实现了有竞争力的性能、强跨领域泛化能力和实用的可扩展性，同时保留了特定领域的精确率。
英文摘要
Event extraction aims to identify event triggers, classify event types, and extract arguments to construct structured event representations. Despite strong in-domain performance, developing models that generalize robustly across domains remains challenging due to variations in contextual expressions and event schemas. Prior unified and multi-task approaches improve in-domain accuracy but exhibit limited flexibility when applied to unseen domains. Even large language model-based methods that provide full event ontologies at inference time often underperform compared to smaller, task-specific fine-tuned models. We propose a unified multi-domain and multi-task training framework that models heterogeneous event schemas within a single model. Our approach introduces domain conditioning signals, jointly with task-specific prompts, enabling dynamic adaptation to dataset-specific schemas without requiring complete event label sets at inference time. The framework supports both pipeline and end-to-end extraction settings, facilitating efficient task- and domain-level transfer. Experiments on diverse event extraction benchmarks demonstrate that our method achieves competitive performance, strong cross-domain generalization, and practical scalability, while preserving domain-specific precision.
