← Go back
Most humans are facing a flood of information every day. However, not every news people read or every fact they are told is actually true. To this end, an automated check of information is needed. The goal of this lecture is to provide students with sinights in Fact Checking approaches. The lecture is structured as follows:
- Text-based approaches
- Knowledge-graph-based approaches
- Hybrid approaches
The course consists of:
- A lecture
The course comprises 2 90min lectures
- A lab
Students are invited to gather practical experiences with SPARQL queries and knowledge-graphs. After that, they should extend the knowledge-graph-based Fact Checking system COPAAL.
- DBPedia SPARQL endpoint
- COPAAL is an open-source knowledge-graph-based Fact Checking system
- Gerber, D., et al.: DeFacto–temporal and multilingual deep fact validation. In: Journal of Web Semantics, Volume 35, Part 2, pp. 85-101. Elsevier, 2015.
- Pasternack, J., Roth, D.: Knowing what to believe (when you already know something). In: Proceedings of the 23rd International Conference on Computational Linguistics, pp. 877-885. ACM, 2010.
- Shi, B., Weninger, T.: Discriminative predicate path mining for fact checking in knowledge graphs. In: Knowledge-Based Systems, Volume 104, pp. 123-133. Elsevier, 2016.
- Shiralkar, P., Flammini, A., Menczer, F., Ciampaglia, G.L.: Finding streams in knowledge graphs to support fact checking. In: 2017 IEEE International Conference on Data Mining (ICDM), pp. 859–864. IEEE, 2017.
- Syed, Z.H., Röder, M., Ngonga Ngomo, A.C.: Unsupervised Discovery of Corroborative Paths for Fact Validation. In: The Semantic Web — ISWC 2019, pp 630-646. Springer, 2019.
- Syed, Z.H., Röder, M., Ngonga Ngomo, A.C.: Factcheck: Validating rdf triples using textual evidence. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pp. 1599–1602. ACM, 2018.