基于检索增强生成的自适应模式感知事件抽取
Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generation
AI总结：
针对事件抽取中模式僵化及缺乏联合评估基准的问题，提出结合模式释义与检索增强生成的ASEE范式，并构建整合12个数据集的MD-SEE基准，显著提升跨场景事件抽取准确性。
摘要：
事件抽取（EE）是自然语言处理（NLP）中的一项基础任务，涉及从非结构化文本中识别和抽取事件信息。现实场景中的有效EE需要两个关键步骤：从数百个候选中选择合适的模式，以及执行抽取过程。现有研究存在两个关键缺口：（1）现有流水线系统中僵化的模式固定问题；（2）缺乏用于评估联合模式匹配与抽取的基准。尽管大语言模型（LLM）提供了潜在解决方案，但其模式幻觉倾向和上下文窗口限制给实际部署带来挑战。为此，我们提出自适应模式感知事件抽取（ASEE），这是一种将模式释义与模式检索增强生成相结合的新颖范式。ASEE能够熟练检索经过释义的模式，并准确生成目标结构。为便于严格评估，我们构建了多维模式感知事件抽取（MD-SEE）基准，该基准系统整合了跨越不同领域、复杂度层级和语言设置的12个数据集。在MD-SEE上的大量评估表明，我们提出的ASEE在各种场景中展现出强大的适应性，显著提升了事件抽取的准确性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
