The European Science Vocabulary
Since its launch in 1994, the CORDIS website has been a crucial platform for European scientific research, providing access to information on EU-funded research projects.
In 2017, CORDIS began investigating the possibilities offered by Natural Language Processing and semantic technologies to improve content classification and accessibility.
Two years later EuroSciVoc (the European Scientific Vocabulary) was born.
What is EuroSciVoc?
EuroSciVoc is a taxonomy used by CORDIS to organise and access information on EU-funded research projects.
It combines advanced technologies like Natural Language Processing (NLP) and Machine Learning to make it easier for users to find relevant information.
By providing a shared vocabulary, harmonizing data, and ensuring compatibility with other systems, EuroSciVoc enhances interoperability within the European research and innovation landscape.
How does EuroSciVoc work?
EuroSciVoc is based on the OECD's Fields of Research and Development (FoRD) classification, which has been expanded to include categories identified in CORDIS content through a semi-automatic NLP process.
The taxonomy is organised in a hierarchical structure, where the first two levels align with the FoRD categories, while the lower levels are composed of categories representing established fields of science including specific or emerging topics as they are discovered in project content.
EuroSciVoc is multilingual and available in six languages: German, English, Spanish, French, Italian, and Polish.
It is adaptable and automatically updates project classifications to the latest taxonomy versions, reflecting the dynamic nature of European research and innovation.
How are projects categorised with EuroSciVoc?
CORDIS uses a custom Semi-Automatic Classification System (SACS) to categorize projects.
SACS employs NLP and Machine Learning techniques to analyse project information, such as titles, abstracts, and results.
The initial categorisation is performed automatically but CORDIS team can validate or refine the categorisation as needed. Since early 2025, registered users can also suggest project categorisation
What are the benefits of using EuroSciVoc?
EuroSciVoc offers several benefits including:
- Improved searchability: Facilitates finding projects related to specific scientific fields.
- Consistency: Provides a uniform classification system for all projects, making it easier to compare and analyse data.
- Adaptability: Automatically updates classifications to stay current with taxonomy changes.
- Reuse: promotes reuse across multiple systems and applications by offering the taxonomy in Simple Knowledge Organisation Systems (SKOS) format.
How can I access and download EuroSciVoc?
EuroSciVoc is publicly accessible via:
- CORDIS Website: The taxonomy is integrated into the CORDIS website, allowing users to search projects by fields of science.
- EU Vocabularies Website: Users can download the taxonomy in SKOS format for reuse.
Who develops and maintains EuroSciVoc?
EuroSciVoc is developed and maintained by the Publications Office of the European Union.
The taxonomy is regularly updated and available on the EU Vocabularies website.
Future perspectives
EuroSciVoc is a key resource for anyone interested in European research and innovation.
Its multilingual capabilities, adaptability, and open-access design make it an essential tool for researchers, developers, and organisations.
As European research continues to evolve, EuroSciVoc will adapt, ensuring it meets new challenges and opportunities.
Plans to transition SACS into an open-source tool aim to engage a broader community of developers and researchers, enhancing collaboration and transparency.