Given a Wikidata revision, is it damaging?
This task is about detecting vandalism as well as all other kinds of damaging edits to Wikidata. In doing so, not only Wikidata's integrity is protected, but also that of all information systems making use of the knowledge base.
Compute relevance scores for triples from type-like relations.
For example, the triple "Johnny_Depp profession Actor" should get a high score, because acting is Depp's main profession, whereas "Quentin_Tarantino profession Actor" should get a low score, because Tarantino is more of a director than an actor. Such scores are a fundamental ingredient when ranking results in entity search.
The task winners will be awarded $1500 each. The respective second and third runner-ups will be awarded $750 and $250. The awards are kindly sponsored by Adobe Systems, Inc. All awards are subject to eligibility terms.
For reproducibility sake, we invite participants to share their code on our GitHub organization. During the competition, private repositories are provided on a first come first served basis, kindly sponsored by GitHub, Inc.