Lost in Recursion: Mining Rich Event Semantics in Knowledge Graphs
This work addresses the challenge of capturing rich semantics in knowledge graphs for complex events like political conflicts, which are often observed indirectly through narratives, offering a method to enhance event understanding in domains such as media analysis or social science.
The paper tackles the problem of constructing and utilizing narratives about complex events from texts, providing a formal representation based on recursive nodes and an algorithm using incremental prompting to mine narratives for different perspectives, with effectiveness demonstrated in a proof of concept.
Our world is shaped by events of various complexity. This includes both small-scale local events like local farmer markets and large complex events like political and military conflicts. The latter are typically not observed directly but through the lenses of intermediaries like newspapers or social media. In other words, we do not witness the unfolding of such events directly but are confronted with narratives surrounding them. Such narratives capture different aspects of a complex event and may also differ with respect to the narrator. Thus, they provide a rich semantics concerning real-world events. In this paper, we show how narratives concerning complex events can be constructed and utilized. We provide a formal representation of narratives based on recursive nodes to represent multiple levels of detail and discuss how narratives can be bound to event-centric knowledge graphs. Additionally, we provide an algorithm based on incremental prompting techniques that mines such narratives from texts to account for different perspectives on complex events. Finally, we show the effectiveness and future research directions in a proof of concept.