Partners
CrossLang
National Technical University of Athens (laboratory Intelligent Systems, Content and Interaction)
Europeana Foundation (Netherlands)
Datoptron (Greece)
FBK (Fondazione Bruno Kessler, Machine Translation Research Unit, Italy)
Translated (Italy)
Datable (Belgium)
Pangeanic (Spain)
University of Leuven (DigitGLAM unit)
European Fashion Heritage Association (Italy)
Institute for Sound and Vision (Netherlands)
Austrian Institute of Technology
Project Description
The consortium of the AI4Culture project (previously named AI4Europeana) is developing a platform which constitutes an online capacity building hub for the application of AI technologies in the cultural heritage sector. The platform offers access to a pool of AI-related resources (such as openly labelled datasets for training and testing AI models), a set of deployable and reusable tools, and capacity building materials. Additionally, the project customises the platform’s components so they can be reused by cultural heritage institutions in the following scenarios:
The role of CrossLang is to perform the project activities related to multilingual text recognition in scanned documents.
- multilingual text recognition in scanned documents
- multilingual subtitles generation and validation
- enrichment with information extracted from images and semantic linking
- machine translation for cultural heritage metadata
The role of CrossLang is to perform the project activities related to multilingual text recognition in scanned documents.
Results
The project runs from April 2023 to February 2025. You can find more information on the Project page.
