linked data publishing

Although scientific data increasingly adhere to the FAIR principles and employ standardized identifiers, practical interoperability remains hindered by heterogeneity in identifier systems and data models. This work proposes and implements two synergistic tools—Babel and ORION—to bridge this gap. Babel constructs clusters of equivalent identifiers through mapping-based clustering and exposes them via a high-performance quantitative API, while ORION standardizes heterogeneous knowledge bases by aligning them to a community-governed common data model. Together, they systematically address the longstanding disconnect between the FAIR “Interoperable” principle and its real-world implementation. The integration of these tools has enabled the construction of a fully interoperable knowledge base, substantially enhancing cross-resource data integration and query capabilities. The resulting framework is publicly available.

Heterogeneous metadata across language resources (LRs) impedes their discoverability and interoperability. Method: This study proposes a unified RDF metadata model integrating the DCAT and META-SHARE ontologies—achieving, for the first time, deep semantic coupling between them. It introduces a novel evaluation paradigm grounded in real user queries (CML) and designs an open-vocabulary-driven, API-based mechanism for machine-readable access. Leveraging the Linked Data technology stack and the Linghub portal, the system supports text search, faceted browsing, and SPARQL querying. Contribution/Results: Empirical evaluation demonstrates significant improvements in LR discoverability, accessibility, and subset extractability; effectively identifies critical metadata heterogeneity issues; and validates that standards-driven ontology integration delivers substantial, measurable gains in LR infrastructure interoperability.

This work addresses the lack of semantic interoperability in structured data (e.g., JSON, YAML, CSV) within scientific workflows, which hinders consistent interpretation. The authors introduce an RDF authoring view in the MetaConfigurator editor that leverages AI-assisted generation of RML mappings to automatically transform structured data into RDF. The system supports triple editing, SPARQL querying, and knowledge graph visualization. Key innovations include the first integration of large language models for natural language-to-SPARQL translation, bidirectional synchronization between JSON-LD and RDF triples, and ontology-aware IRI auto-completion. Demonstrated on MOF synthesis experiments, the approach successfully converts JSON protocols into semantic knowledge graphs, enabling interactive exploration of relationships between experimental conditions and outcomes, thereby significantly lowering the barrier to adopting Semantic Web technologies.

This study addresses the lack of a clear definition for low-resource languages in the Semantic Web, which exacerbates inequalities in multilingual open data. To bridge this gap, the work proposes a reproducible, multi-tiered classification framework that quantifies language resources by integrating data from multiple sources—DBpedia, BabelNet, and Wikidata—within the context of Linked Open Data knowledge graphs. The framework evaluates languages along three dimensions: language coverage, number of entities, and cross-lingual transfer potential, categorizing them into low-, medium-, and high-resource tiers. This systematic approach not only fills a critical void in assessing language resource availability in the Semantic Web but also provides empirical guidance for selecting target languages in cross-lingual knowledge transfer tasks.

This study addresses the fragmentation of academic data across isolated databases, which suffers from inconsistent metadata and missing cross-source linkages. To overcome these challenges, the authors construct a locally deployable academic data lake based on DuckDB and Parquet, integrating eight major open scholarly sources and harmonizing approximately 293 million publications through DOI standardization. They introduce a novel cross-source unified query architecture and propose an innovative scientific ontology alignment method leveraging BGE-large embeddings, achieving an F1 score of 0.77 while covering 99.8% of research topics—significantly outperforming traditional text-matching baselines. The resulting dataset spans 960 GB, encompasses 22 schemas and 153 SQL views, and undergoes rigorous multi-dimensional validation (both automated and manual), enabling sophisticated cross-source scholarly analysis.

This work proposes a declarative configuration–based approach to automatically generate compliant REST APIs, significantly reducing development costs for standardized academic infrastructure such as SKG-IF. Built upon the Python framework RAMOSE, the method uniquely enables joint queries across RDF and non-RDF data sources within a single API operation using arbitrary keys. It integrates multi-source orchestration, pluggable output formatting, paginated caching, OpenAPI specification export, and authenticated write capabilities. The system includes a built-in SKG-IF compliance module, allowing standard-compliant interfaces to be deployed through configuration alone. In practice, it powers the OpenCitations API—handling peak loads of nearly 38 million monthly requests—and underpins the GRAPHIA project’s SKG-IF federated system, demonstrating superior performance compared to nine existing tools.

Traditional document-centric structures hinder the structuring, updating, and reuse of knowledge, while existing formal methods struggle to gain widespread adoption due to their neglect of human–machine usability. This work proposes the MMM data model, which combines lightweight normative constraints with free-text tags to enable cross-disciplinary and cross-application knowledge interoperability without enforcing rigid semantic uniformity. By introducing a decentralized knowledge architecture that preserves expressive freedom, the model balances human readability with system interoperability. A reference implementation and pilot deployments across multiple disciplines demonstrate the approach’s feasibility and preliminary effectiveness, offering a novel paradigm for building interoperable, decentralized knowledge communities.

This work addresses the limitations of existing ontology alignment approaches and the difficulty large language models (LLMs) face in effectively leveraging formal ontological knowledge by proposing an open-source ontology engineering system that integrates LLMs, OWL reasoning, and stable matching. The key innovation lies in a structured tool-access mechanism based on the Model Context Protocol (MCP), which circumvents direct parsing of raw OWL files by the LLM and instead formulates ontology alignment as a stable one-to-one matching problem. Implemented in Rust, the system achieves an F1 score of 0.832 (precision: 0.963) on the OAEI Anatomy track and 0.438 on the Conference track. Experimental results demonstrate that the structured tool-access approach significantly improves alignment performance, elevating F1 from 0.323 to 0.717, thereby validating the efficacy and superiority of the proposed method.

This work addresses the lack of a lightweight, OWL 2 DL-compatible foundational ontology capable of supporting complex modeling in Semantic Web knowledge graphs by proposing gUFO—the first lightweight implementation of the Unified Foundational Ontology (UFO) fully compliant with OWL 2 DL. gUFO innovatively integrates the OntoClean typology, a reification mechanism for intrinsic and relational properties, and formal constructs for situational and higher-order type modeling, achieving a balance between expressivity and reasoning compatibility. Its axiomatization adheres to ISO/IEC standards, with rigor ensured through reification patterns and constraints on the type hierarchy. Empirical evaluation demonstrates successful deployment across multiple research and industrial projects, with systematic assessment confirming that gUFO surpasses existing OWL-based implementations such as BFO and DOLCE in both modeling expressiveness and practical utility.

Existing RDF systems lack standardized message boundaries in event-driven and streaming contexts, resulting in poor interoperability and inefficient processing. This work proposes the concept of “RDF Messages,” formally defining, for the first time, a message structure with RDF datasets as atomic units and explicitly delineating message boundaries to support streaming, storage, and reproducible replay. Built upon W3C Semantic Web standards, the approach introduces a unified encapsulation mechanism that operates across serialization and transport layers, complemented by configuration profiles that describe message structure and processing policies. The proposed framework effectively enables incremental consumption in scenarios such as IoT observations and SPARQL CONSTRUCT results, laying the foundation for RDF message streams and logs while advancing related W3C standardization efforts.