A challenge in fact checking is the ability to provide explanations for the claim validation. We present a computational method that uses reference information to verify claims and explain its assessments. Our solution exploits existing formal representation of knowledge to generate interpretable explanations for the fact checking decisions.
Explainable fact checking with probabilistic answer set programming
GFAIH 2019, Invited Talk at Global Forum on AI for Humanity, 28-30 October 2019, Paris, France
© EURECOM. Personal use of this material is permitted. The definitive version of this paper was published in GFAIH 2019, Invited Talk at Global Forum on AI for Humanity, 28-30 October 2019, Paris, France and is available at :
PERMALINK : https://www.eurecom.fr/publication/6047