An assertion and alignment correction framework for large scale knowledge bases

Semantic web

article

Jiaoyan Chen¹  Ernesto Jiménez-Ruiz²  Ian Horrocks¹  Xi Chen⁴  Erik Bryhn Myklebust³ 

[1] Department of Computer Science, University of Oxford;City, University of London;Centre for Scalable Data Access ,(SIRIUS), University of Oslo;Jarvis Lab Tencent;Norwegian Institute for Water Research

关键词: Knowledge base;    assertion correction;    alignment correction;    semantic embedding;    constraints;   

DOI  :  10.3233/SW-210448

来源: IOS Press

【 摘 要 】

Various knowledge bases (KBs) have been constructed via information extraction from encyclopedias, text and tables, as well as alignment of multiple sources. Their usefulness and usability is often limited by quality issues. One common issue is the presence of erroneous assertions and alignments, often caused by lexical or semantic confusion. We study the problem of correcting such assertions and alignments, and present a general correction framework which combines lexical matching, context-aware sub-KB extraction, semantic embedding, soft constraint mining and semantic consistency checking. The framework is evaluated with one set of literal assertions from DBpedia, one set of entity assertions from an enterprise medical KB, and one set of mapping assertions from a music KB constructed by integrating Wikidata, Discogs and MusicBrainz. It has achieved promising results, with a correction rate (i.e., the ratio of the target assertions/alignments that are corrected with right substitutes) of 70.1%, 60.9% and 71.8%, respectively.

【 授权许可】

Unknown