增强事件链接的事件候选获取

中文摘要 AI 辅助

事件链接将文本中的事件提及与知识库（KB）中的条目关联起来，或将其识别为知识库外事件。尽管现有方法采用不同的架构，但候选事件获取仍可能因简短模糊的提及、嘈杂的参数以及对于检索而言效用不均的证据而受到削弱。我们提出了MACE，一种多智能体候选事件获取方法，在链接之前细化事件结构。MACE使用证据专长的LLM智能体来获取时间、地点、参与者和事件类型证据，将中间查询暴露给候选事件查找工具，并让协调者在最终候选构建之前修订证据集。在两个事件链接基准上的实验表明，将MACE添加到不同的事件链接模型中能持续提高准确性。这些结果表明，MACE通过更好的候选事件获取来改进事件链接，而无需修改事件链接模型。

英文摘要

Event linking associates event mentions in text with entries in a knowledge base (KB), or identifies them as out-of-KB events. Although existing methods use different architectures, candidate event acquisition can still be weakened by short ambiguous mentions, noisy arguments, and evidence that is unevenly useful for retrieval. We present MACE, a Multi-Agent Candidate Event acquisition method that refines event structure before linking. MACE uses evidence-specialized LLM agents to acquire time, location, participant, and event-type evidence, exposes intermediate queries to candidate-event lookup tools, and lets a coordinator revise the evidence set before final candidate construction. Experiments on two event linking benchmarks show that adding MACE to different event linking models consistently improves accuracy. These results show that MACE improves event linking through better candidate event acquisition without modifying the event linking model.

发表机构

• Northeastern University（东北大学）

机构由 AI 辅助整理，请以论文原文为准。