Abstract
Events describe the state changes of entities. In a document, multiple events are connected by various relations (e.g., Coreference, Temporal, Causal, and Subevent). Therefore, obtaining the connections between events through Event-Event Relation Extraction (ERE) is critical to understand natural language. There are two main problems in the current ERE works: a. Only embeddings of the event triggers are used for event feature representation, ignoring event arguments (e.g., time, place, person, etc.) and their structure within the event. b. The interconnection between relations (e.g., temporal and causal relations usually interact with each other ) is ignored. To solve the above problems, this paper proposes a jointly multiple ERE framework called GraphERE based on Graph-enhanced Event Embeddings. First, we enrich the event embeddings with event argument and structure features by using static AMR graphs and IE graphs; Then, to jointly extract multiple event relations, we use Node Transformer and construct Task-specific Dynamic Event Graphs for each type of relation. Finally, we used a multi-task learning strategy to train the whole framework. Experimental results on the latest MAVEN-ERE dataset validate that GraphERE significantly outperforms existing methods. Further analyses indicate the effectiveness of the graph-enhanced event embeddings and the joint extraction strategy.
Abstract (translated)
事件描述了实体状态的变化。在文档中,多个事件通过各种关系(如共指、时间、因果关系和子事件)相互连接。因此,通过事件-事件关系提取(ERE)获得事件之间的连接对于理解自然语言非常重要。当前ERE工作的两个主要问题是:a. 只有事件嵌入被用于事件特征表示,忽略了事件参数(例如,时间、地点、人物等)及其在事件中的结构。b. 关系之间的相互作用(例如,时间和因果关系通常相互交互)被忽视。为解决上述问题,本文提出了一种基于图增强事件嵌入的多任务框架,称为GraphERE。首先,我们通过使用静态AMR图和IE图丰富事件嵌入;然后,为了共同提取多个事件关系,我们使用节点Transformer并为每种关系构建了任务特定的动态事件图。最后,我们使用多任务学习策略训练整个框架。对最新MAVEN-ERE数据集的实验结果证实,GraphERE显著优于现有方法。进一步的分析表明,图形增强的事件嵌入和联合提取策略的有效性。
URL
https://arxiv.org/abs/2403.12523