EPCI: An Embedding Method for Post-Correction of Inconsistency in the RDF Knowledge Bases. Issue 2 (4th March 2022)

• Record Type: Journal Article
• Authors: Abedini, Farhad; Keyvanpour, Mohammad Reza; Menhaj, Mohammad Bagher
• Is Part Of: IETE journal of research. Volume 68:Issue 2(2022)
• Page Start: 1043
• Page End: 1055
• Publication Date: 2022-03-04
• Subjects: Embedding -- Error correction -- Inconsistency -- Knowledge graph -- RDF knowledge base; Electronics -- Periodicals; Telecommunication -- Periodicals; Electronics; Telecommunication; Periodicals; 621.38
• DOI: 10.1080/03772063.2019.1634495
• Languages: English
• ISSNs: 0377-2063

Abstract

Abstract : There are many methods for the RDF knowledge base correction in which errors are detected and then deleted or repaired if necessary. Although most of them do only detection and deletion of the errors and do not pay attention to repair. There are only a few methods to repair these errors that their accuracy is not acceptable. To solve this problem, a method will be proposed with a suitable accuracy that is called EPCI. The focus of EPCI is on inconsistency errors correction because previous correction methods have paid less attention to these kinds of errors. Most of its existing studies avoid these errors before knowledge base creation in the form of pre-correction. Although in some cases, it is needed to correct these errors after its creation as post-correction. For this reason, in EPCI a post-correction method is proposed for this objective. In the studied post-correction methods so far it has not been mentioned that inconsistency can be solved with the embedding methods and most of them solved only numeric inconsistencies. Nowadays, embedding methods are rapidly growing with high precision. So in EPCI, this technique will be used to solve also the problem of non-numeric inconsistent triples.