@inproceedings{JannidisRegerWeimeretal.2015,
  author    = {Jannidis, Fotis and Reger, Isabella and Weimer, Lukas and Krug, Markus and Puppe, Frank},
  title     = {Automatische Erkennung von Figuren in deutschsprachigen Romanen},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-143332},
  pages     = {7},
  year      = {2015},
  abstract  = {Eine wichtige Grundlage f{\"u}r die quantitative Analyse von Erz{\"a}hltexten, etwa eine Netzwerkanalyse der Figurenkonstellation, ist die automatische Erkennung von Referenzen auf Figuren in Erz{\"a}hltexten, ein Sonderfall des generischen NLP-Problems der Named Entity Recognition. Bestehende, auf Zeitungstexten trainierte Modelle sind f{\"u}r literarische Texte nur eingeschr{\"a}nkt brauchbar, da die Einbeziehung von Appellativen in die Named Entity-Definition und deren h{\"a}ufige Verwendung in Romantexten zu einem schlechten Ergebnis f{\"u}hrt. Dieses Paper stellt eine anhand eines manuell annotierten Korpus auf deutschsprachige Romane des 19. Jahrhunderts angepasste NER-Komponente vor.},
  subject      = {Digital Humanities},
  language  = {de}
}
@article{ReulChristHarteltetal.2019,
  author    = {Reul, Christian and Christ, Dennis and Hartelt, Alexander and Balbach, Nico and Wehner, Maximilian and Springmann, Uwe and Wick, Christoph and Grundig, Christine and B{\"u}ttner, Andreas and Puppe, Frank},
  title     = {OCR4all—An open-source tool providing a (semi-)automatic OCR workflow for historical printings},
  series = {Applied Sciences},
  volume    = {9},
  journal   = {Applied Sciences},
  number    = {22},
  issn      = {2076-3417},
  doi       = {10.3390/app9224853},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-193103},
  pages     = {4853},
  year      = {2019},
  abstract  = {Optical Character Recognition (OCR) on historical printings is a challenging task mainly due to the complexity of the layout and the highly variant typography. Nevertheless, in the last few years, great progress has been made in the area of historical OCR, resulting in several powerful open-source tools for preprocessing, layout analysis and segmentation, character recognition, and post-processing. The drawback of these tools often is their limited applicability by non-technical users like humanist scholars and in particular the combined use of several tools in a workflow. In this paper, we present an open-source OCR software called OCR4all, which combines state-of-the-art OCR components and continuous model training into a comprehensive workflow. While a variety of materials can already be processed fully automatically, books with more complex layouts require manual intervention by the users. This is mostly due to the fact that the required ground truth for training stronger mixed models (for segmentation, as well as text recognition) is not available, yet, neither in the desired quantity nor quality. To deal with this issue in the short run, OCR4all offers a comfortable GUI that allows error corrections not only in the final output, but already in early stages to minimize error propagations. In the long run, this constant manual correction produces large quantities of valuable, high quality training material, which can be used to improve fully automatic approaches. Further on, extensive configuration capabilities are provided to set the degree of automation of the workflow and to make adaptations to the carefully selected default parameters for specific printings, if necessary. During experiments, the fully automated application on 19th Century novels showed that OCR4all can considerably outperform the commercial state-of-the-art tool ABBYY Finereader on moderate layouts if suitably pretrained mixed OCR models are available. Furthermore, on very complex early printed books, even users with minimal or no experience were able to capture the text with manageable effort and great quality, achieving excellent Character Error Rates (CERs) below 0.5\%. The architecture of OCR4all allows the easy integration (or substitution) of newly developed tools for its main components by standardized interfaces like PageXML, thus aiming at continual higher automation for historical printings.},
  language  = {en}
}
@article{HarteltPuppe2022,
  author    = {Hartelt, Alexander and Puppe, Frank},
  title     = {Optical Medieval Music Recognition using background knowledge},
  series = {Algorithms},
  volume    = {15},
  journal   = {Algorithms},
  number    = {7},
  issn      = {1999-4893},
  doi       = {10.3390/a15070221},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-278756},
  year      = {2022},
  abstract  = {This paper deals with the effect of exploiting background knowledge for improving an OMR (Optical Music Recognition) deep learning pipeline for transcribing medieval, monophonic, handwritten music from the 12th-14th century, whose usage has been neglected in the literature. Various types of background knowledge about overlapping notes and text, clefs, graphical connections (neumes) and their implications on the position in staff of the notes were used and evaluated. Moreover, the effect of different encoder/decoder architectures and of different datasets for training a mixed model and for document-specific fine-tuning based on an extended OMR pipeline with an additional post-processing step were evaluated. The use of background models improves all metrics and in particular the melody accuracy rate (mAR), which is based on the insert, delete and replace operations necessary to convert the generated melody into the correct melody. When using a mixed model and evaluating on a different dataset, our best model achieves without fine-tuning and without post-processing a mAR of 90.4\%, which is raised by nearly 30\% to 93.2\% mAR using background knowledge. With additional fine-tuning, the contribution of post-processing is even greater: the basic mAR of 90.5\% is raised by more than 50\% to 95.8\% mAR.},
  language  = {en}
}
@article{Puppe2022,
  author    = {Puppe, Frank},
  title     = {Gesellschaftliche Perspektiven einer fachspezifischen KI f{\"u}r automatisierte Entscheidungen},
  series = {Informatik Spektrum},
  volume    = {45},
  journal   = {Informatik Spektrum},
  number    = {2},
  issn      = {0170-6012},
  doi       = {10.1007/s00287-022-01443-6},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-324197},
  pages     = {88-95},
  year      = {2022},
  abstract  = {Die k{\"u}nstliche Intelligenz (KI) entwickelt sich rasant und hat bereits eindrucksvolle Erfolge zu verzeichnen, darunter {\"u}bermenschliche Kompetenz in den meisten Spielen und vielen Quizshows, intelligente Suchmaschinen, individualisierte Werbung, Spracherkennung, -ausgabe und -{\"u}bersetzung auf sehr hohem Niveau und hervorragende Leistungen bei der Bildverarbeitung, u. a. in der Medizin, der optischen Zeichenerkennung, beim autonomen Fahren, aber auch beim Erkennen von Menschen auf Bildern und Videos oder bei Deep Fakes f{\"u}r Fotos und Videos. Es ist zu erwarten, dass die KI auch in der Entscheidungsfindung Menschen {\"u}bertreffen wird; ein alter Traum der Expertensysteme, der durch Lernverfahren, Big Data und Zugang zu dem gesammelten Wissen im Web in greifbare N{\"a}he r{\"u}ckt. Gegenstand dieses Beitrags sind aber weniger die technischen Entwicklungen, sondern m{\"o}gliche gesellschaftliche Auswirkungen einer spezialisierten, kompetenten KI f{\"u}r verschiedene Bereiche der autonomen, d. h. nicht nur unterst{\"u}tzenden Entscheidungsfindung: als Fußballschiedsrichter, in der Medizin, f{\"u}r richterliche Entscheidungen und sehr spekulativ auch im politischen Bereich. Dabei werden Vor- und Nachteile dieser Szenarien aus gesellschaftlicher Sicht diskutiert.},
  subject      = {K{\"u}nstliche Intelligenz},
  language  = {de}
}