基于跨层级多视角特征的多语言事件探测  

Multilingual Event Detection Based on Cross-level and Multi-view Features Fusion

作　　者：张志远 张维彦 宋雨秋 阮彤[1] ZHANG Zhiyuan;ZHANG Weiyan;SONG Yuqiu;RUAN Tong(School of Information Science and Engineering,East China University of Science and Technology,Shanghai 200237,China)

机构地区：[1]华东理工大学信息工程与科学学院,上海200237

出　　处：《计算机科学》2024年第5期208-215,共8页Computer Science

摘　　要：多语言事件探测任务的目标是将多种语言的新闻文档集合组织成不同的关键事件,其中每个事件可以包含不同语言的新闻文档。该任务有助于各种下游任务应用,如多语言知识图谱构建、事件推理、信息检索等。目前,多语言事件探测主要分为先翻译再事件探测与先单语言检测再跨多种语言对齐两种方法,前者依赖翻译的效果,后者需要为每种语言单独训练模型。为此,提出了一种名为基于跨层级多视角特征融合的多语言事件探测方法,端到端地进行多语言事件探测任务。该方法从不同层级利用文档的多视角特征,获得了高可靠性的多语言事件探测结果并提升了低资源语言事件探测的泛化性能。在9种语言混合的新闻数据集上进行的实验表明,所提方法的BCubed F1值提升了4.63%。The goal of the multilingual event detection task is to organize a collection of news documents in multiple languages into different key events,where each event can include news documents in different languages.This task facilitates various downstream task applications,such as multilingual knowledge graph construction,event reasoning,information retrieval,etc.At pre-sent,multilingual event detection is mainly divided into two methods:translation first and then event detection,and single language detection first and then alignment across multiple languages.The former relies on the effect of translation while the latter requires a separate training model for each language.To this end,this paper proposes a multilingual event detection method based on cross-level multi-view feature fusion,which performs end-to-end multilingual event detection tasks.This method uses the multi-view features of documents from different levels to obtain high reliability.It improves the generalization performance of low-resource language event detection.Experiments on a news dataset with a mixture of nine languages show that the proposed method improves the BCubed F1 value by 4.63%.

关 键 词：多语言预训练模型 多语言事件探测 新闻文档聚类 加权相似度 增量聚类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]