What is Event Knowledge Graph: A Survey
This work addresses the need for a systematic understanding of event-centric knowledge representation for researchers and practitioners in fields like search, recommendation, and text generation, but it is incremental as it synthesizes existing literature rather than introducing new methods.
This survey paper tackles the problem of characterizing Event Knowledge Graphs (EKGs) by providing a comprehensive overview from historical, ontological, and application perspectives, with the result being a structured analysis of EKG development, trends, and future research directions.
Besides entity-centric knowledge, usually organized as Knowledge Graph (KG), events are also an essential kind of knowledge in the world, which trigger the spring up of event-centric knowledge representation form like Event KG (EKG). It plays an increasingly important role in many downstream applications, such as search, question-answering, recommendation, financial quantitative investments, and text generation. This paper provides a comprehensive survey of EKG from history, ontology, instance, and application views. Specifically, to characterize EKG thoroughly, we focus on its history, definition, schema induction, acquisition, related representative graphs/systems, and applications. The development processes and trends are studied therein. We further summarize prospective directions to facilitate future research on EKG.