Poster Presentation at the CLARIN Conference

Our Team Member Klara Venglarova presented her doctoral work Processing Digitized Text on an Example of Job Advertisements from Austrian Periodicals from 1850-1950, which is part of the JobAds project, at the annual CLARIN conference in Vösendorf, Austria. She was describing the pipeline developed within the project, from corpus selection, image pre-proprocessing, layout analysis and OCR, to job advertisements identification and classification, and extraction of job titles from the identified job advertisements. Discussions with participating researchers confirmed that the process of turning scanned images into machine-readable text is a current issue dealt with in many institutions and the project thus has a lot to offer.