A Conceptual Model for Attributions in Event-Centric Knowledge Graphs
Florian Plötzky, Katarina Britz, Wolf-Tilo Balke
TL;DR
This paper tackles the challenge of representing viewpoint-dependent and disputed information within Event-Centric Knowledge Graphs (ECKGs) to support narrative reasoning. It introduces attributions—parameterized predicates tied to specific viewpoints—paired with viewpoint hierarchies to govern how facts and claims fuse across perspectives. The authors formalize core concepts (viewpoints, stances, consensus, refinements, attributions, claims, and viewpoint-compatibility) and present two hierarchy variants, Viewpoint-Preserving Hierarchies and Winner-Takes-All Hierarchies, along with a practical case study on the Russo-Ukrainian War. The work demonstrates how such a model can represent diverse, potentially conflicting narratives while maintaining internal consistency, using standard Semantic Web techniques like singleton properties for reification. It lays groundwork for more robust narrative reasoning and downstream tasks in multi-perspective domains, while acknowledging limitations related to time dynamics, data sparsity, and the need for real-world implementation and evaluation.
Abstract
The use of narratives as a means of fusing information from knowledge graphs (KGs) into a coherent line of argumentation has been the subject of recent investigation. Narratives are especially useful in event-centric knowledge graphs in that they provide a means to connect different real-world events and categorize them by well-known narrations. However, specifically for controversial events, a problem in information fusion arises, namely, multiple viewpoints regarding the validity of certain event aspects, e.g., regarding the role a participant takes in an event, may exist. Expressing those viewpoints in KGs is challenging because disputed information provided by different viewpoints may introduce inconsistencies. Hence, most KGs only feature a single view on the contained information, hampering the effectiveness of narrative information access. This paper is an extension of our original work and introduces attributions, i.e., parameterized predicates that allow for the representation of facts that are only valid in a specific viewpoint. For this, we develop a conceptual model that allows for the representation of viewpoint-dependent information. As an extension, we enhance the model by a conception of viewpoint-compatibility. Based on this, we deepen our original deliberations on the model's effects on information fusion and provide additional grounding in the literature.