Construction of Knowledge Graphs: Current State and Challenges
Построение графов знаний: современное состояние и проблемы
2024-08-22
SCID: 54.1/7r325xu5
Discuss with AI
incremental KG updatesknowledge graph constructionmetadata managementontology developmentquality assurance
Figures from the paper
Abstract (AI)
With Knowledge Graphs (KGs) at the center of numerous applications such as recommender systems and question-answering, the need for generalized pipelines to construct and continuously update such KGs is increasing. While the individual steps that are necessary to create KGs from unstructured sources (e.g., text) and structured data sources (e.g., databases) are mostly well researched for their one-shot execution, their adoption for incremental KG updates and the interplay of the individual steps have hardly been investigated in a systematic manner so far. In this work, we first discuss the main graph models for KGs and introduce the major requirements for future KG construction pipelines. Next, we provide an overview of the necessary steps to build high-quality KGs, including cross-cutting topics such as metadata management, ontology development, and quality assurance. We then evaluate the state of the art of KG construction with respect to the introduced requirements for specific popular KGs, as well as some recent tools and strategies for KG construction. Finally, we identify areas in need of further research and improvement.
Key Findings
1
Existing KG construction methods are comparatively well studied for one-shot creation, but incremental updating and coordination among pipeline steps remain insufficiently investigated.
2
Further research is needed to improve the systematic interplay, maintainability, and updateability of KG construction processes.
3
High-quality KG construction involves extraction and integration steps plus cross-cutting capabilities including metadata management, ontology development, and quality assurance.
4
Knowledge graph construction requires generalized pipelines capable of integrating unstructured and structured sources while supporting continuous incremental updates.
5
The work organizes major KG graph models and derives requirements for future construction pipelines, then evaluates popular KGs, tools, and strategies against those requirements.
Research Object
Knowledge graph construction pipelines (processes for building and updating Knowledge Graphs from unstructured and structured sources)
Research Subject
the requirements, workflow steps, quality, and systematic integration of knowledge graph construction and continuous-update processes
Publication Details
Publication Date
2024-08-22
Journal
Publisher
ISSN
Cited by
121
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai15
Distributed Representations of Words and Phrases and their Compositionality2013
The FAIR Guiding Principles for scientific data management and stewardship2016
Overcoming catastrophic forgetting in neural networks2017
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing2022
Knowledge Graph Embedding by Translating on Hyperplanes2014
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications2021
Unifying Large Language Models and Knowledge Graphs: A Roadmap2024
A Review of Relational Machine Learning for Knowledge Graphs2015
Knowledge graph refinement: A survey of approaches and evaluation methods2016
A Survey on Application of Knowledge Graph2020
Industry-scale Knowledge Graphs: Lessons and Challenges2019
Defining a Knowledge Graph Development Process Through a Systematic Review2022
Large Language Models and Knowledge Graphs: Opportunities and Challenges2023
Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations (Short Paper)2023
Qualitative Spatial Reasoning over Questions (Short Paper)2022