@inproceedings{759b77b9826e49a79d9d18508490647f,
title = "Representativeness of knowledge bases with the generalized benford{\textquoteright}s law",
abstract = "Knowledge bases (KBs) such as DBpedia, Wikidata, and YAGO contain a huge number of entities and facts. Several recent works induce rules or calculate statistics on these KBs. Most of these methods are based on the assumption that the data is a representative sample of the studied universe. Unfortunately, KBs are biased because they are built from crowdsourcing and opportunistic agglomeration of available databases. This paper aims at approximating the representativeness of a relation within a knowledge base. For this, we use the generalized Benford{\textquoteright}s law, which indicates the distribution expected by the facts of a relation. We then compute the minimum number of facts that have to be added in order to make the KB representative of the real world. Experiments show that our unsupervised method applies to a large number of relations. For numerical relations where ground truths exist, the estimated representativeness proves to be a reliable indicator.",
author = "Arnaud Soulet and Arnaud Giacometti and B{\'e}atrice Markhoff and Suchanek, \{Fabian M.\}",
note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2018.; 17th International Semantic Web Conference, ISWC 2018 ; Conference date: 08-10-2018 Through 12-10-2018",
year = "2018",
month = jan,
day = "1",
doi = "10.1007/978-3-030-00671-6\_22",
language = "English",
isbn = "9783030006709",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "374--390",
editor = "Su{\'a}rez-Figueroa, \{Mari Carmen\} and Valentina Presutti and Lucie-Aimee Kaffee and Elena Simperl and Marta Sabou and Denny Vrandecic and Irene Celino and Kalina Bontcheva",
booktitle = "The Semantic Web – ISWC 2018 - 17th International Semantic Web Conference, 2018, Proceedings",
}