FIZ KDAI Research GroupOur student co-worker Nele Garay presented a joint poster on "Named Entity Recognition for Digitised Archival Documents in German" with @MahsaVafaie & @lysander07 at #EKAW24 in Amsterdam. Great job, Nele!
This poster is part of the important work @fiz_karlsruhe is doing within the project "Themenportal Wiedergutmachung nationalsozialistischen Unrechts"
poster paper: https://zenodo.org/records/14419994
@ekawconference #ai #llms #knowledgegraphs #semanticweb @fiz_karlsruhe
Named Entity Recognition for digitised archival documents in German
This paper presents an experiment that evaluates the effectiveness of two different Named Entity Recognition(NER) tools at extracting entities directly from the output of an Optical Character Recognition (OCR) workflow.The authors initially developed a test dataset comprising both raw and corrected OCR outputs, which weremanually annotated with tags for Person, Location, and Organisation. Subsequently, they applied each NER toolto both the raw and corrected OCR outputs, evaluating their performance by comparing the precision, recall, andF1 scores against the manually annotated data.
Marco Rospocher
David M. Schmidt
DICE
