E-Periodica – Next Level Access
Aim of the project
Expanded and improved research functions will be implemented on the E-Periodica platform on the basis of named entity recognition, named entity linking and automated OCR correction.
Description of the project
The Periodica: Next Level Access project seeks to develop additional research and analysis options using automated text enhancement. A backend system generates functions including the named entity recognition of individuals, place and country names and named entity linking (IAF - Integrated Authority File) of the entities recognised. In addition, automated OCR corrections will be applied to all journal holdings. At frontend level, the enhancements and associated features such as links to further information will be made visible and usable.
Synergies and context
- Existing data stock of E-Periodica (full-text files, 7 million pages)
- Pilot project in the field of text recognition, conducted in 2017
- Research cooperation in the field of text recognition
Time frame
- By late 2019: Implementation of the initial concept phase, after which the realisation of further phases will be decided.
- By late 2021/2022: Development of the backend system and implementation of advanced frontend research options.
