Unflattening Knowledge Graphs
Open Access
- 5 December 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 223-224
Abstract
Large general-purpose knowledge graphs (KGs) are a critical component for knowledge-driven applications. However, most KGs represent only a limited view of the entities and concepts they describe. The concept coffee can, for example, refer to the plant that yields coffee seeds, the beverage ‘coffee’, and the activity of drinking the beverage. Moreover, it has a long history that is deeply connected to colonialism and status. All of these notions are an intricate part of national identities, have changed dramatically over time, and connect to many different narratives with different opinions on them. This complexity is not captured in current KGs. In this vision paper, I present the three crucial challenges for unflattening knowledge graphs and directions for future work.Keywords
Funding Information
- European Commission (101088548)
This publication has 9 references indexed in Scilit:
- Automated Concatenation of Embeddings for Structured Prediction2021
- Open Knowledge Enrichment for Long-tail Entities2020
- Injecting Semantic Background Knowledge into Neural Networks using Graph Embeddings2017
- Marrying Uncertainty and Time in Knowledge GraphsProceedings of the AAAI Conference on Artificial Intelligence, 2017
- A Contextualised Semantics for owl:sameAs2016
- Ad Hoc Monitoring of Vocabulary Shifts over Time2015
- A knowledge‐based approach to Information Extraction for semantic interoperability in the archaeology domainJournal of the Association for Information Science and Technology, 2015
- The Shifting Discourse of the European Central Bank: Exploring Structural Space in Semantic Networks2014
- Concept drift and how to identify itJournal of Web Semantics, 2011