EventKGE: Event knowledge graph embedding with event causal transfer

Traditional knowledge graph embedding (KGE) aims to map entities and relations into continuous space vectors to provide high-quality data feature representation for downstream tasks. However, relations in most KGs often only reflect connections between static entities, but cannot represent dynamic activities and state changes of related entities, which makes the KGE models unable to effectively learn rich and comprehensive entity representation. In this paper, we verify the importance of embedding event knowledge in KG representation learning, and propose a novel event KGE model based on event causal transfer (EventKGE), which can effectively maintain the semantic information of events, entities, and relations in the event KG. First, we define a six tuple-based event representation model consisting of event trigger words, event arguments and event description text, which can effectively express events in a structured form. Second, for a given event KG, the event nodes and entity nodes in the KG are integrated through the constructed heterogeneous graph. Meanwhile, in the heterogeneous graph, the event nodes and entity nodes are connected through the event arguments type, and the event nodes are connected through the causal relationship. Finally, an information transfer method based on an attention network is designed, which is used for the relations between events, events and entities, and entities and entities, to integrate event information into KGE. Comprehensive experiments on the ACE2005 corpus and CEC2.0 dataset verify that the event KGE model we designed is efficient and stable in multiple downstream tasks.