HighlightPeerJ Computer Science

Evaluating FAIR Digital Object and Linked Data as distributed object systems

A paper evaluating the FAIR Digital Object concept and its implementations.

The authors evaluate FAIR Digital Object (FDO) as a global distributed object system using five conceptual frameworks. They compare FDO with established Linked Data practices and Web architecture, providing recommendations for both communities. The paper discusses the history of the Semantic Web and its relevance to FDO adoption.

Based on: Evaluating FAIR Digital Object and Linked Data as distributed object systems · PeerJ Computer Science

HighlightInformation

Construction of Knowledge Graphs: Current State and Challenges

A research paper on the current state and challenges of constructing knowledge graphs.

The authors discuss the main graph models for knowledge graphs, introduce requirements for future construction pipelines, and evaluate the state-of-the-art. They identify areas in need of further research and improvement. The paper provides an overview of necessary steps to build high-quality knowledge graphs, including metadata management and quality assurance.

Based on: Construction of Knowledge Graphs: Current State and Challenges · Information

Highlightopenalex.org

Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization

A paper introducing SMART-SLIC, a domain-specific LLM framework integrating RAG with KG and vector store.

The authors present SMART-SLIC, a framework that combines retrieval-augmented generation (RAG) with knowledge graphs (KG) and vector stores to improve question answering accuracy in specific domains. The framework is designed to be generalizable and adaptable to various specialized domains. It aims to mitigate hallucinations, reduce fine-tuning needs, and attribute information sources.

Based on: Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization

HighlightarXiv (Cornell University)

From human experts to machines: An LLM supported approach to ontology and knowledge graph construction

Paper exploring the semi-automatic construction of Knowledge Graphs using Large Language Models.

The authors propose a pipeline for constructing Knowledge Graphs with minimal human involvement, leveraging open-source Large Language Models. They demonstrate their method on a deep learning methodology dataset. The paper evaluates the generated content and suggests that LLMs can reduce human effort in KG construction.

Based on: From human experts to machines: An LLM supported approach to ontology and knowledge graph construction · arXiv (Cornell University)

Highlightopenalex.org

TrumorGPT: Query Optimization and Semantic Reasoning over Networks for Automated Fact-Checking

A generative AI solution for automated fact-checking that merges machine learning with natural language processing techniques.

The paper introduces TrumorGPT, a novel framework for automated fact-checking. It leverages a large language model with few-shot learning and retrieval-augmented generation to access updated knowledge graphs. This approach aims to combat misinformation by providing accurate and reliable information promptly.

Based on: TrumorGPT: Query Optimization and Semantic Reasoning over Networks for Automated Fact-Checking

HighlightInstitution of Engineering and Technology eBooks

Knowledge representation and reasoning in personal knowledge graphs

A chapter discussing the semantic web stack and its application to personal knowledge graphs.

The authors describe the semantic web stack, a set of open standards for representing and reasoning with knowledge graphs.,They discuss projects using these standards to build personal knowledge graphs that interoperate with other knowledge graphs on the web.,Related standards for describing rules and policies are also discussed.

Based on: Knowledge representation and reasoning in personal knowledge graphs · Institution of Engineering and Technology eBooks

HighlightarXiv (Cornell University)

Construction of Knowledge Graphs: State and Challenges

A research paper on the construction and updating of knowledge graphs.

The authors discuss graph models, requirements for KG construction pipelines, and necessary steps to build high-quality KGs. They evaluate the state-of-the-art and identify areas in need of further research. The paper provides an overview of the individual steps involved in creating and updating KGs from unstructured and structured data sources.

Based on: Construction of Knowledge Graphs: State and Challenges · arXiv (Cornell University)

HighlightLecture notes in computer science

The SAREF Pipeline and Portal—An Ontology Verification Framework

A framework for ontology verification presented in a lecture notes publication.

This paper introduces the SAREF pipeline and portal, an ontology verification framework. The authors describe the framework's components and its application to ontology validation. The framework is designed to facilitate the verification of ontologies and their integration with other knowledge graphs.

Based on: The SAREF Pipeline and Portal—An Ontology Verification Framework · Lecture notes in computer science

HighlightLNCS / ISWC

Ontology Repositories and Semantic Artefact Catalogues with OntoPortal Technology

A paper on the OntoPortal Alliance consortium's platforms for ontology management.

The OntoPortal Alliance consortium provides common platforms for receiving, hosting, serving, aligning, and enabling reuse of ontologies and semantic artefacts.,These platforms make ontologies FAIR (Findable, Accessible, Interoperable, Reusable).,They address the growing need for governance of exploding number of semantic artefacts in science.

Based on: Ontology Repositories and Semantic Artefact Catalogues with OntoPortal Technology · LNCS / ISWC

HighlightAutomation in Construction

Semantic Rule Checking of Cross-Domain Building Data Using SHACL

Uses SHACL for semantic rule checking across cross-domain building data.

This paper explores the application of SHACL shapes constraint language for semantic rule checking in construction industry. It presents a production deployment demonstrating SHACL validation. The study focuses on linked document delivery and information containers.

Based on: Semantic Rule Checking of Cross-Domain Building Data Using SHACL · Automation in Construction

HighlightData Intelligence (MIT Press)

The W3C Data Catalog Vocabulary Version 2: Rationale Design Principles and Uptake

W3C RDF vocabulary for data catalog interoperability.

DCAT v2 addresses gaps identified through implementation experience across communities, building on the 2014 W3C Recommendation. It supports wide adoption, especially with FAIR data principles. The vocabulary enables data catalog interoperability.

Based on: The W3C Data Catalog Vocabulary Version 2: Rationale Design Principles and Uptake · Data Intelligence (MIT Press)

HighlightJournal of Biomedical Semantics

DCSO: towards an ontology for machine-actionable data management plans

Paper proposing the DMP Common Standard Ontology (DCSO) as a serialisation of the DCS core concepts.

The authors propose the DMP Common Standard Ontology (DCSO) to represent Data Management Plans as machine-actionable artefacts. The ontology is based on the Research Data Alliance DMP Common Standard and aims to provide a standardised way to describe controlled vocabularies. The paper reports on a community effort to create the DCSO, which can become a suitable candidate for a reference serialisation of the DMP Common Standard.

Based on: DCSO: towards an ontology for machine-actionable data management plans · Journal of Biomedical Semantics