提出自适应事件抽取框架，能动态选型并精准生成事件结构。
Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generation
- 通过检索改写后的事件模式，动态匹配合适模板
- 在12个跨领域数据集上准确率显著提升
- 适合需要灵活应对多类型事件的工业级应用
事件抽取（EE）是自然语言处理中的基础任务，旨在从非结构化文本中识别并提取事件信息。实际场景下的有效EE需完成两个关键步骤：从数百个候选模式中选择合适模式，并执行抽取。现有研究存在两大缺陷：（1）管道系统中模式固定僵化；（2）缺乏联合评估模式匹配与抽取的基准。尽管大模型具备潜力，但其模式幻觉和上下文窗口限制制约了落地。为此，我们提出自适应模式感知事件抽取（ASEE），结合模式改写与检索增强生成的新范式。ASEE可精准检索改写后的模式并生成目标结构。为支持严格评估，我们构建了多维模式感知事件抽取（MD-SEE）基准，系统整合12个跨领域、多复杂度、多语言设置的数据集。在MD-SEE上的大量实验表明，所提ASEE在多种场景下展现强适应性，显著提升事件抽取准确率。
原文摘要 · Abstract (English)
Event extraction (EE) is a fundamental task in natural language processing (NLP) that involves identifying and extracting event information from unstructured text. Effective EE in real-world scenarios requires two key steps: selecting appropriate schemas from hundreds of candidates and executing the extraction process. Existing research exhibits two critical gaps: (1) the rigid schema fixation in existing pipeline systems, and (2) the absence of benchmarks for evaluating joint schema matching and extraction. Although large language models (LLMs) offer potential solutions, their schema hallucination tendencies and context window limitations pose challenges for practical deployment. In response, we propose Adaptive Schema-aware Event Extraction (ASEE), a novel paradigm combining schema paraphrasing with schema retrieval-augmented generation. ASEE adeptly retrieves paraphrased schemas and accurately generates targeted structures. To facilitate rigorous evaluation, we construct the Multi-Dimensional Schema-aware Event Extraction (MD-SEE) benchmark, which systematically consolidates 12 datasets across diverse domains, complexity levels, and language settings. Extensive evaluations on MD-SEE show that our proposed ASEE demonstrates strong adaptability across various scenarios, significantly improving the accuracy of event extraction.
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。