利用文档级信息结合语义空间加强事件检测

• 作 者: 罗锦尚 时昕 吴洁 侯孟书
• 机 构: 电子科技大学信息中心 成都 611731;电子科技大学计算机科学与工程学院 成都 611731
• 出 处: 电子科技大学学报
• 发表日期: 2022年2期
• 关键词: BERT document-level information event detection semantic space

事件检测(ED)是事件抽取的一项基础任务,旨在检测事件触发器并进行分类.现有事件检测方法主要基于句子级信息,忽略了句子间的事件相关性.文档级信息有助于减轻语义歧义与加强上下文理解,为此,提出一种新颖的事件检测框架,命名为document embedding networks combined with semantic space (DENSS).首先,利用了预训练语言模型,分别表示具有丰富语义信息的事件类型与事件触发器;设计一种多层次注意力机制,用以捕获句子级和文档级信息;映射事件类型与事件触发器的特征向量到一个共享的语义空间,事件的相关性被表示为事件嵌入的距离;最后,基于基准数据集进行了验证,结果表明该方法优于大部分已有的方法,以及具有共享语义空间的文档级信息对于加强事件检测的有效性.“,”Event detection (ED) is a fundamental task of event extraction, which aims to detect triggers in text and determine their event types. Most existing methods regard event detection as a sentence-level classification problem, ignoring the correlations between events in different sentences. A novel event detection framework, named document embedding networks combined with semantic space (DENSS), is proposed in this paper. The document-level information is utilized to alleviate semantic ambiguity and enhance contextual understanding. Specifically, the representations of event types and triggers are obtained through an off-the-shelf pre-trained model and a designed multi-level attention mechanism. Then the feature vectors of event types and triggers are mapped into a shared semantic space, where the distance represents the correlation of different events. The experimental results on the benchmark dataset demonstrate that our method outperforms most existing methods, and justify the effectiveness of document-level information with shared semantic space.