The mission of the GOBLIN COST Action is to enhance the quality, coverage, and accessibility of open knowledge graphs—particularly DBpedia—by uniting Europe’s knowledge graph communities in a coordinated effort to support multilingual, cross-domain, and FAIR (Findable, Accessible, Interoperable, Reusable) knowledge infrastructures.
Goals
- Increase Accuracy and Coverage: Improve the quality and scope of knowledge graphs across languages and domains, with a strong emphasis on under-resourced languages.
- Foster Collaboration and Coordination: Align efforts across national DBpedia chapters and other knowledge graph initiatives to avoid duplication and harmonize practices.
- Empower Communities and Stakeholders: Build capacity and provide tools to researchers, developers, SMEs, and public institutions for creating and using knowledge graphs.
- Bridge Knowledge Graphs and AI: Support the integration of knowledge graphs with AI technologies, including large language models, to improve interpretability, reliability, and multilingual capabilities.
- Support Innovation and Sustainability: Encourage the development of new applications and services, and promote long-term sustainability through training, documentation, and best practices.
Description of Working Groups (WGs)
The GOBLIN Action is organized into five specialized Working Groups, each addressing a key aspect of knowledge graph development and use:
WG1: Knowledge Graphs Engineering
Focuses on the technical foundations of knowledge graph creation, including:
- Ontology modelling and representation
- Knowledge extraction and enrichment
- Data integration and interlinking
- Publishing workflows and release management
WG2: Knowledge Graphs Management
Addresses operational and quality-related aspects of knowledge graphs, such as:
- Data quality assurance and cleansing
- Metadata and provenance tracking
- Knowledge exploration, access control, and security
- Graph mining for new knowledge discovery
WG3: Knowledge Graph-aware Services and Methods
Explores how knowledge graphs can enhance and be enhanced by AI technologies, with topics including:
- Integration with deep learning and large language models
- Applications in machine translation, question answering, and information retrieval
WG4: Use Cases and Applications
Investigates practical applications of knowledge graphs across diverse domains, such as:
- Linguistics and language preservation
- News, media, and social media
- E-commerce and finance
- Life sciences and cultural heritage
- Social sciences and education
WG5: Action Management and Dissemination
Ensures smooth coordination, stakeholder engagement, and dissemination through:
- Strategic planning and reporting
- Training and capacity building
- Outreach, communication, and stakeholder collaboration