Fact validation with knowledge graph embeddings

Ammar Ammar, Remzi Celebi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations


Fact validation in a knowledge graph is a task to determine whether a given fact (subject, predicate, object) should appear in the knowledge graph. In this paper, we have described our approach for the fact validation task in the context of the Semantic Web Challenge 2019. We used embedding features with machine learning to predict facts that were missing from the knowledge graph. The embedding features were generated applying a knowledge graph method known as the RDF2Vec method on the knowledge graph with only positive statements. To improve our machine learning model, we added the test facts that we could validate via the public sources into the positive knowledge graph. We trained a Random Forest classifier on the training data (positive and negative statements) plus the verified test statements and made predictions for test data.
Original languageEnglish (US)
Title of host publication2019 ISWC Satellite Tracks (Posters and Demonstrations, Industry, and Outrageous Ideas), ISWC 2019-Satellites
Number of pages4
StatePublished - Jan 1 2019
Externally publishedYes


Dive into the research topics of 'Fact validation with knowledge graph embeddings'. Together they form a unique fingerprint.

Cite this