TL;DR本研究提出了一种名为 Story Salads 的方法，可用于自动从多个文档中提取相关信息并形成连贯的叙述，该方法可应用于自然灾害和冲突中信息获取的场景，此外，该研究还探索了创新的聚类任务，提出了考虑全局上下文和连贯性的新方法，表明简单的词袋相似性聚类方法在本任务中效果不佳。
Abstract
During natural disasters and conflicts, information about what happened is
often confusing, messy, and distributed across many sources. We would like to
be able to automatically identify relevant information and