Knowledge Graph Curation: A Practical Framework

TL;DR

This paper proposes a practical framework for improving knowledge graph quality through metrics, cleaning, duplicate detection, and fusion strategies, aiming to enhance their reliability for various applications.

Contribution

It introduces a comprehensive, actionable framework for knowledge graph curation, including quality assessment, validation, duplicate detection, and fusion techniques.

Findings

Defined quality metrics for KGs

Outlined verification and validation processes

Presented strategies for duplicate detection and knowledge fusion

Abstract

Knowledge Graphs (KGs) have shown to be very important for applications such as personal assistants, question-answering systems, and search engines. Therefore, it is crucial to ensure their high quality. However, KGs inevitably contain errors, duplicates, and missing values, which may hinder their adoption and utility in business applications, as they are not curated, e.g., low-quality KGs produce low-quality applications that are built on top of them. In this vision paper, we propose a practical knowledge graph curation framework for improving the quality of KGs. First, we define a set of quality metrics for assessing the status of KGs, Second, we describe the verification and validation of KGs as cleaning tasks, Third, we present duplicate detection and knowledge fusion strategies for enriching KGs. Furthermore, we give insights and directions toward a better architecture for curating KGs.