TY - GEN
T1 - Towards Knowledge Graphs Validation Through Weighted Knowledge Sources
AU - Huaman, Elwin
AU - Tauqeer, Amar
AU - Fensel, Anna
PY - 2021
Y1 - 2021
N2 - The performance of applications, such as personal assistants and search engines, relies on high-quality knowledge bases, a.k.a. Knowledge Graphs (KGs). To ensure their quality one important task is knowledge validation, which measures the degree to which statements or triples of KGs are semantically correct. KGs inevitably contain incorrect and incomplete statements, which may hinder their adoption in business applications as they are not trustworthy. In this paper, we propose and implement a Validator that computes a confidence score for every triple and instance in KGs. The computed score is based on finding the same instances across different weighted knowledge sources and comparing their features. We evaluate our approach by comparing its results against a baseline validation. Our results suggest that we can validate KGs with an f-measure of at least 75%. Time-wise, the Validator, performed a validation of 2530 instances in 15 min approximately. Furthermore, we give insights and directions toward a better architecture to tackle KG validation.
AB - The performance of applications, such as personal assistants and search engines, relies on high-quality knowledge bases, a.k.a. Knowledge Graphs (KGs). To ensure their quality one important task is knowledge validation, which measures the degree to which statements or triples of KGs are semantically correct. KGs inevitably contain incorrect and incomplete statements, which may hinder their adoption in business applications as they are not trustworthy. In this paper, we propose and implement a Validator that computes a confidence score for every triple and instance in KGs. The computed score is based on finding the same instances across different weighted knowledge sources and comparing their features. We evaluate our approach by comparing its results against a baseline validation. Our results suggest that we can validate KGs with an f-measure of at least 75%. Time-wise, the Validator, performed a validation of 2530 instances in 15 min approximately. Furthermore, we give insights and directions toward a better architecture to tackle KG validation.
KW - Knowledge graph assessment
KW - Knowledge graph curation
KW - Knowledge graph validation
U2 - 10.1007/978-3-030-91305-2_4
DO - 10.1007/978-3-030-91305-2_4
M3 - Conference paper
AN - SCOPUS:85121594430
SN - 9783030913045
T3 - Communications in Computer and Information Science
SP - 47
EP - 60
BT - Knowledge Graphs and Semantic Web - 3rd Iberoamerican Conference and 2nd Indo-American Conference, KGSWC 2021, Proceedings
A2 - Villazón-Terrazas, Boris
A2 - Ortiz-Rodríguez, Fernando
A2 - Tiwari, Sanju
A2 - Goyal, Ayush
A2 - Jabbar, M.
PB - Springer
CY - Cham
T2 - 3rd Iberoamerican Knowledge Graph and Semantic Web Conference and the 2nd Indo-American Knowledge Graphs and Semantic Web Conference, KGSWC 2021
Y2 - 22 November 2021 through 24 November 2021
ER -