Knowledge bases are becoming essential components for tasks that require automation with some degrees of intelligence. It is crucial to establish automatic and timely checks to ensure highlevel quality of the knowledge base content (i.e., entities, types, and relations). In this paper, we present KBQ, a tool that automates the detection and report generation of quality issues for evolving knowledge bases. KBQ analyzes the evolution of a KB by measuring the frequency of change, the change pattern, the change impact and the causes of changes of resources and properties. Data collection and profiling tasks are performed using Loupe, an online tool for linked data profiling. We describe KBQ in action on two different use cases, and we report the benefits that it introduced. KBQ is published as open source project, and a demo is available at http://datascience.ismb.it/shiny/KBQ/.

KBQ - A Tool for Knowledge Base Quality Assessment Using Evolution Analysis / Rashid, MOHAMMAD RIFAT AHMMAD; Rizzo, Giuseppe; Mihindukulasooriya, Nandana; Torchiano, Marco; Corcho, Oscar. - ELETTRONICO. - 2065:(2017), pp. 58-63. ((Intervento presentato al convegno Ninth International Conference on Knowledge Capture tenutosi a Austin (USA) nel December 4th, 2017.

KBQ - A Tool for Knowledge Base Quality Assessment Using Evolution Analysis

Mohammad Rashid;Giuseppe Rizzo;Marco Torchiano;
2017

Abstract

Knowledge bases are becoming essential components for tasks that require automation with some degrees of intelligence. It is crucial to establish automatic and timely checks to ensure highlevel quality of the knowledge base content (i.e., entities, types, and relations). In this paper, we present KBQ, a tool that automates the detection and report generation of quality issues for evolving knowledge bases. KBQ analyzes the evolution of a KB by measuring the frequency of change, the change pattern, the change impact and the causes of changes of resources and properties. Data collection and profiling tasks are performed using Loupe, an online tool for linked data profiling. We describe KBQ in action on two different use cases, and we report the benefits that it introduced. KBQ is published as open source project, and a demo is available at http://datascience.ismb.it/shiny/KBQ/.
File in questo prodotto:
File Dimensione Formato  
paper13.pdf

accesso aperto

Descrizione: Main article
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 838.32 kB
Formato Adobe PDF
838.32 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11583/2701827