Lost in Recursion: Mining Rich Event Semantics in Knowledge Graphs

TL;DR

This paper introduces a formal method to construct and utilize narratives of complex events in knowledge graphs, capturing multiple perspectives and levels of detail through recursive nodes, with an algorithm for mining these narratives from texts.

Contribution

It presents a novel formal representation of event narratives with recursive nodes and an incremental prompting algorithm for extracting multi-perspective narratives from texts.

Findings

Effective narrative construction demonstrated in proof of concept

Algorithm successfully mines multi-level event narratives from texts

Future research directions outlined for enhancing narrative integration

Abstract

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.