The ELC-DHLR (Enhancing Library Collections for Digital Humanities and Language Research) project brings together Czech and Swiss partners from the international research infrastructures CLARIN and DARIAH. Its goal is to make extensive digitized library collections available for modern scientific research in the fields of the digital humanities and linguistics.
In recent decades, millions of digitized documents have been created in Europe. However, their use for advanced research often faces a number of practical obstacles, such as poor-quality optical character recognition (OCR), limited metadata, or a lack of integration with analytical tools. The ELC-DHLR project aims to remove these barriers and create an environment that will enable more effective work with digital cultural heritage.
Modern technologies, particularly large language models (LLMs), play a key role in the project. They enable automatic document summarization, semantic search, metadata enrichment, and intelligent discovery of connections within large-scale digital collections. The project also links digitized library collections with advanced language and corpus tools, which will enable researchers to analyze large volumes of text data. These existing tools will be further enhanced with new LLM-based features that will simplify access to digitized collections for both experts and the general public.
The project also includes the development of new technological infrastructure that will ensure the secure handling, management, and sharing of data in accordance with the international FAIR principles (findability, accessibility, interoperability, and reusability of data). Researchers will have access to new tools for creating their own datasets, searching for information, and performing advanced analyses.
Another important aspect of the project is international cooperation and the sharing of expertise between Czech and Swiss institutions. The project also includes workshops and educational activities designed for students, researchers, and research infrastructure staff. ELC-DHLR will thus contribute to better utilization of digitized library collections and strengthen the conditions for modern scientific research.
Abstract and Project Objectives
The project aims to make digitised library collections truly research-ready for digital humanities and language sciences. Building on Czech and Swiss infrastructure consortia for CLARIN and DARIAH, it will enhance the collections and create a sustainable and user-friendly ecosystem aligned with FAIR principles.
The core goals are:
- Develop advanced transformation and enrichment technologies – improve metadata and structural segmentation, integrate enrichment services, and introduce Large Language Models for automated summarisation, semantic search, and intelligent exploration.
- Ensure structured storage and seamless access – build secure repositories, interoperable APIs, and a Research Workspace within the Kramerius system to allow researchers to create customised datasets and export data in multiple formats.
- Advance analytical capabilities – develop an AI-powered assistant that bridges natural language queries with corpus engines.
- Foster knowledge exchange and community engagement – organise workshops to connect technical outputs with researchers, students and other research infrastructure staff, and promote best practices across infrastructures.
- Strengthen international cooperation – leverage the expertise of specialists in the Czech Republic and Switzerland to ensure knowledge transfer and methodological innovation.
Through these goals, ELC-DHLR will unlock the potential of centuries of cultural heritage, ensuring that digitised collections can be effectively used for advanced cross-disciplinary research. The project will also contribute to strengthening the cooperation between leading research organizations in CZ and CH in the field of digital humanities and language research.
| Beneficiary | Charles University (LINDAT/CLARIAH) |
| Project partner(s) (Czech Republic) | Library Czech Academy of Sciences
Moravian Library, Brno National Library of the Czech Republic |
| Project partner(s) (Switzerland) | University of Zurich (UZH)
University of Basel (Unibas) ETH Zurich, ETH Library (ETHZ) |
| Project duration | 1.4.2026–31.12.2028 |
| Main project location | Charles University, Prague |
| Project website | https://elc-dhlr.lib.cas.cz/ |
| Website: The Second Swiss Contribution | https://www.swiss-contribution.cz/en/ |
| Total eligible project costs | CZK 29,965,000 |
| Of which 85% from the Swiss contribution | CZK 25,470,250 |
| Project ID | 8K0201 |
