Search results

There is an increasing interest in the use of knowledge graphs to represent real-world knowledge and a common need to manage imprecise knowledge in many real-world applications. This paper aims to study approaches to solve flexible queries over knowledge graphs.

By introducing fuzzy logic in the query answering process, the authors are able to obtain a novel algorithm to solve flexible queries over knowledge graphs. This approach is implemented in the FUzzy Knowledge Graphs system, a software tool with an intuitive user-graphical interface.

This approach makes it possible to reuse semantic web standards (RDF, SPARQL and OWL 2) and builds a fuzzy layer on top of them. The application to a use case shows that the system can aggregate information in different ways by selecting different fusion operators and adapting to different user needs.

This approach is more general than similar previous works in the literature and provides a specific way to represent the flexible restrictions (using fuzzy OWL 2 datatypes).

The purpose of this work is to explore the new possibilities enabled by the recent introduction of RDF-star, an extension that allows for statements about statements within the Resource Description Framework (RDF). Alongside Named Graphs, this approach offers opportunities to leverage a meta-level for data modeling and data applications.

In this extended paper, the authors build onto three modeling use cases published in a previous paper: (1) provide provenance information, (2) maintain backwards compatibility for existing models, and (3) reduce the complexity of a data model. The authors present two scenarios where they implement the use of the meta-level to extend a data model with meta-information.

The authors present three abstract patterns for actively using the meta-level in data modeling. The authors showcase the implementation of the meta-level through two scenarios from our research project: (1) the authors introduce a workflow for triple annotation that uses the meta-level to enable users to comment on individual statements, such as for reporting errors or adding supplementary information. (2) The authors demonstrate how adding meta-information to a data model can accommodate highly specialized data while maintaining the simplicity of the underlying model.

Through the formulation of data modeling patterns with RDF-star and the demonstration of their application in two scenarios, the authors advocate for data modelers to embrace the meta-level.

With RDF-star being a very new extension to RDF, to the best of the authors’ knowledge, they are among the first to relate it to other meta-level approaches and demonstrate its application in real-world scenarios.

This research aimed to visualize and analyze the co-word network and thematic clusters of the intellectual structure in the field of linked data during 1900–2021.

This applied research employed a descriptive and analytical method, scientometric indicators, co-word techniques, and social network analysis. VOSviewer, SPSS, Python programming, and UCINet software were used for data analysis and network structure visualization.

The top ranks of the Web of Science (WOS) subject categorization belonged to various fields of computer science. Besides, the USA was the most prolific country. The keyword ontology had the highest frequency of co-occurrence. Ontology and semantic were the most frequent co-word pairs. In terms of the network structure, nine major topic clusters were identified based on co-occurrence, and 29 thematic clusters were identified based on hierarchical clustering. Comparisons between the two clustering techniques indicated that three clusters, namely semantic bioinformatics, knowledge representation, and semantic tools were in common. The most mature and mainstream thematic clusters were natural language processing techniques to boost modeling and visualization, context-aware knowledge discovery, probabilistic latent semantic analysis (PLSA), semantic tools, latent semantic indexing, web ontology language (OWL) syntax, and ontology-based deep learning.

This study adopted various techniques such as co-word analysis, social network analysis network structure visualization, and hierarchical clustering to represent a suitable, visual, methodical, and comprehensive perspective into linked data.

Despite ongoing research into archival metadata standards, digital archives are unable to effectively represent records in their appropriate contexts. This study aims to propose a knowledge graph that depicts the diverse relationships between heterogeneous digital archive entities.

This study introduces and describes a method for applying knowledge graphs to digital archives in a step-by-step manner. It examines archival metadata standards, such as Records in Context Ontology (RiC-O), for characterising digital records; explains the process of data refinement, enrichment and reconciliation with examples; and demonstrates the use of knowledge graphs constructed using semantic queries.

This study introduced the 97imf.kr archive as a knowledge graph, enabling meaningful exploration of relationships within the archive’s records. This approach facilitated comprehensive record descriptions about different record entities. Applying archival ontologies with general-purpose vocabularies to digital records was advised to enhance metadata coherence and semantic search.

Most digital archives serviced in Korea are limited in the proper use of archival metadata standards. The contribution of this study is to propose a practical application of knowledge graph technology for linking and exploring digital records. This study details the process of collecting raw data on archives, data preprocessing and data enrichment, and demonstrates how to build a knowledge graph connected to external data. In particular, the knowledge graph of RiC-O vocabulary, Wikidata and Schema.org vocabulary and the semantic query using it can be applied to supplement keyword search in conventional digital archives.

The purpose of this article is to contribute to the digital development and utilization of China’s intangible cultural heritage resources, research on the theft of intangible cultural heritage resources and knowledge integration based on linked data is proposed to promote the standardized description of intangible cultural heritage knowledge and realize the digital dissemination and development of intangible cultural heritage.

In this study, firstly, the knowledge organization theory and semantic Web technology are used to describe the intangible cultural heritage digital resource objects in metadata specifications. Secondly, the ontology theory and technical methods are used to build a conceptual model of the intangible cultural resources field and determine the concept sets and hierarchical relationships in this field. Finally, the semantic Web technology is used to establish semantic associations between intangible cultural heritage resource knowledge.

The study findings indicate that the knowledge organization of intangible cultural heritage resources constructed in this study provides a solution for the digital development of intangible cultural heritage in China. It also provides semantic retrieval with better knowledge granularity and helps to visualize the knowledge content of intangible cultural heritage.

This study summarizes and provides significant theoretical and practical value for the digital development of intangible cultural heritage and the resource description and knowledge fusion of intangible cultural heritage can help to discover the semantic relationship of intangible cultural heritage in multiple dimensions and levels.

With the increasing complexity of public–private partnership (PPP) projects, the amount of data generated during the construction process is massive. This paper aims to develop a new information management method to cope with the risk problems involved in dealing with such data, based on domain ontologies of the construction industry, to help manage PPP risks, share and reuse risk knowledge.

Risk knowledge concepts are acquired and summarized through PPP failure cases and an extensive literature review to establish a domain framework for risk knowledge using ontology technology to help manage PPP risks.

The results indicate that the risk ontology is capable of capturing key concepts and relationships involved in managing PPP risks and can be used to facilitate knowledge reuse and storage beneficial to risk management.

The classes in the risk knowledge ontology model constructed in this research do not yet cover all the information in PPP project risks and need to be further extended. Moreover, only the framework and basic methods needed are developed, while the construction of a working ontology model and the relationship between implicit and explicit knowledge is a complicated process that requires repeated modifications and evaluations before it can be implemented.

The ontology provides a basis for turning PPP risk information into risk knowledge to allow the effective sharing and communication of project risks between different project stakeholders. It can also have the potential to help reduce the dependence on subjectivity by mining, using and storing tacit knowledge in the risk management process.

The apparent suitability of the nine classes of PPP risk knowledge (project model, risk type, risk occurrence stage, risk source, risk consequence, risk likelihood, risk carrier, risk management measures and risk case) is identified, and the proposed construction method and steps for a complete domain ontology for PPP risk management are unique. A combination of criteria- and task-based evaluations is also developed for assessing the PPP risk ontology for the first time.

Adequate means for easily viewing, browsing and searching knowledge graphs (KGs) are a crucial, still limiting factor. Therefore, this paper aims to present virtual properties as valuable user interface (UI) concept for ontologies and KGs able to improve these issues. Virtual properties provide shortcuts on a KG that can enrich the scope of a class with other information beyond its direct neighborhood.

Virtual properties can be defined as enhancements of shapes constraint language (SHACL) property shapes. Their values are computed on demand via protocol and RDF query language (SPARQL) queries. An approach is demonstrated that can help to identify suitable virtual property candidates. Virtual properties can be realized as integral functionality of generic, frame-based UIs, which can automatically provide views and masks for viewing and searching a KG.

The virtual property approach has been implemented at Bosch and is usable by more than 100,000 Bosch employees in a productive deployment, which proves the maturity and relevance of the approach for Bosch. It has successfully been demonstrated that virtual properties can significantly improve KG UIs by enriching the scope of a class with information beyond its direct neighborhood.

SHACL-defined virtual properties and their automatic identification are a novel concept. To the best of the author’s knowledge, no such approach has been established nor standardized so far.

MITRE and the National Security Agency cooperatively developed and maintained a D3FEND knowledge graph (KG). It provides concepts as an entity from the cybersecurity countermeasure domain, such as dynamic, emulated and file analysis. Those entities are linked by applying relationships such as analyze, may_contains and encrypt. A fundamental challenge for collaborative designers is to encode knowledge and efficiently interrelate the cyber-domain facts generated daily. However, the designers manually update the graph contents with new or missing facts to enrich the knowledge. This paper aims to propose an automated approach to predict the missing facts using the link prediction task, leveraging embedding as representation learning.

D3FEND is available in the resource description framework (RDF) format. In the preprocessing step, the facts in RDF format converted to subject–predicate–object triplet format contain 5,967 entities and 98 relationship types. Progressive distance-based, bilinear and convolutional embedding models are applied to learn the embeddings of entities and relations. This study presents a link prediction task to infer missing facts using learned embeddings.

Experimental results show that the translational model performs well on high-rank results, whereas the bilinear model is superior in capturing the latent semantics of complex relationship types. However, the convolutional model outperforms 44% of the true facts and achieves a 3% improvement in results compared to other models.

Despite the success of embedding models to enrich D3FEND using link prediction under the supervised learning setup, it has some limitations, such as not capturing diversity and hierarchies of relations. The average node degree of D3FEND KG is 16.85, with 12% of entities having a node degree less than 2, especially there are many entities or relations with few or no observed links. This results in sparsity and data imbalance, which affect the model performance even after increasing the embedding vector size. Moreover, KG embedding models consider existing entities and relations and may not incorporate external or contextual information such as textual descriptions, temporal dynamics or domain knowledge, which can enhance the link prediction performance.

Link prediction in the D3FEND KG can benefit cybersecurity countermeasure strategies in several ways, such as it can help to identify gaps or weaknesses in the existing defensive methods and suggest possible ways to improve or augment them; it can help to compare and contrast different defensive methods and understand their trade-offs and synergies; it can help to discover novel or emerging defensive methods by inferring new relations from existing data or external sources; and it can help to generate recommendations or guidance for selecting or deploying appropriate defensive methods based on the characteristics and objectives of the system or network.

The representation learning approach helps to reduce incompleteness using a link prediction that infers possible missing facts by using the existing entities and relations of D3FEND.

The curation of ontologies and knowledge graphs (KGs) is an essential task for industrial knowledge-based applications, as they rely on the contained knowledge to be correct and error-free. Often, a significant amount of a KG is curated by humans. Established validation methods, such as Shapes Constraint Language, Shape Expressions or Web Ontology Language, can detect wrong statements only after their materialization, which can be too late. Instead, an approach that avoids errors and adequately supports users is required.

For solving that problem, Property Assertion Constraints (PACs) have been developed. PACs extend the range definition of a property with additional logic expressed with SPARQL. For the context of a given instance and property, a tailored PAC query is dynamically built and triggered on the KG. It can determine all values that will result in valid property value assertions.

PACs can avoid the expansion of KGs with invalid property value assertions effectively, as their contained expertise narrows down the valid options a user can choose from. This simplifies the knowledge curation and, most notably, relieves users or machines from knowing and applying this expertise, but instead enables a computer to take care of it.

PACs are fundamentally different from existing approaches. Instead of detecting erroneous materialized facts, they can determine all semantically correct assertions before materializing them. This avoids invalid property value assertions and provides users an informed, purposeful assistance. To the author's knowledge, PACs are the only such approach.