统一框架实现跨领域事件抽取，动态适配不同任务与领域
A Multi-Domain and Multi-Task Generative Framework with Explicit Task and Domain Conditioning for Cross-Domain Event Extraction
- 用任务和领域条件信号引导模型，无需完整标签集即可适应新数据
- 在多个基准上表现接近最优，跨领域泛化能力显著优于基线
- 适合需要灵活迁移的事件抽取场景，尤其适用于多领域部署
事件抽取旨在识别事件触发词、分类事件类型并提取论元，构建结构化事件表示。尽管现有方法在单领域内表现良好，但跨领域泛化仍面临挑战，主要源于上下文表达和事件模式的差异。以往的统一或多项式方法虽提升了单领域精度，但在未见领域上灵活性不足。即使基于大语言模型的方法能提供完整的事件本体，其性能仍常低于小型专用微调模型。我们提出一种统一的多领域、多任务训练框架，能在单一模型中建模异构事件模式。通过引入领域条件信号与任务特定提示，实现对数据集特有模式的动态适应，且推理时无需完整事件标签集。该框架支持流水线与端到端两种设置，促进任务与领域的高效迁移。在多个事件抽取基准上的实验表明，该方法在保持领域特异性精度的同时，实现了具有竞争力的性能、强大的跨领域泛化能力以及实际可扩展性。
原文摘要 · Abstract (English)
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.
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。