Previous Research

The DFG-funded project "Development of a Model Repository and Automatic Font Recognition for OCR-D" aims to improve the recognition rates of OCR procedures for historical prints. Since existing models have usually been trained either on the basis of modern corpora or unfiltered historical corpora with a large variety of fonts, the extent to which they suited for this task is limited. By training font-specific OCR models, the aim is to improve the reliability of text recognition in image digitisations of historical prints.

More information on the project can be found in the corresponding GEPRIS entry. The project is part of our former research focus "OCR & Layout Recognition".

Publications:

• Weichselbaumer, N., Seuret, M., Limbach, S., Dong, R., Burghardt, M. & Christlein, V. (2020). New Approaches to OCR for Early Printed Books. In DigItalia 1-2020, DOI: 10.36181/DIGITALIA-00014

Papers:

OCR and Layout Recognition, i.e. the automated transformation of scans of physical text documents into machine-readable, digital documents, plays a crucial role in the Digital Humanities, especially when it comes to computational research into historical sources.

Publications:

• Weichselbaumer, N., Seuret, M., Limbach, S., Dong, R., Burghardt, M. & Christlein, V. (2020). New Approaches to OCR for Early Printed Books. In DigItalia 1-2020, DOI: 10.36181/DIGITALIA-00014
• Liebl, B. & Burghardt, M. (2020). From Historical Newspapers to Machine-Readable Data: The Origami OCR Pipeline. Proceedings of the 1st Workshop on Computational Humanities Research (CHR).
• Liebl, B. & Burghardt, M. (2020). An Evaluation of DNN Architectures for Page Segmentation of Historical Newspapers. 25th International Conference on Pattern Recognition, Mailand. (Preprint arxiv.org/abs/2004.07317)
• Lehenmeier, C., Burghardt, M. & Mischka, B. (2020). Layout Detection and Table Recognition – Recent Challenges in Digitizing Historical Documents and Handwritten Tabular Data. 24th International Conference on Theory and Practice of Digital Libraries, Lyon.

In this area we use computational approaches to digitise and analyse symbolic music (sheet music).

Publications:

• Burghardt, M. & Fuchs, F. (2019). A Computational Approach to Analyzing Musical Complexity of the Beatles. In Book of Abstracts, DH 2019.
• Burghardt, M. (2018). Digital Humanities in der Musikwissenschaft – Computer-gestützte Erschließungsstrategien und Analyseansätze für handschriftliche Liedblätter. In B. Wiermann & A. Bonte (Hrsg.): Bibliothek. Forschung und Praxis, Sonderheft “Digitale Forschungsinfrastruktur für die Musikwissenschaft” (Preprint).
• Burghardt, M. & Lamm, L. (2017). Entwicklung eines Music Information Retrieval-Tools zur Melodic Similarity-Analyse deutschsprachiger Volkslieder. GI Workshop „Musik trifft Informatik“, INFORMATIK 2017, Chemnitz.
• Burghardt, M. & Spanner, S. (2017). Allegro: User-centered Design of a Tool for the Crowdsourced Transcription of Handwritten Music Scores. Proceedings of the DATeCH (Digital Access to Textual Cultural Heritage) conference. ACM.
• Burghardt, M., Spanner, S., Schmidt, T., Fuchs, F., Buchhop, K., Nickl, M. & Wolff, C. (2017). Digitale Erschließung einer Sammlung von Volksliedern aus dem deutschsprachigen Raum. In Book of Abstracts, DHd 2017.
• Burghardt, M., Lamm, L., Lechler, D., Schneider, M. & Semmelmann, T. (2016). Tool based Identification of Melodic Patterns in MusicXML Documents. In Book of Abstracts of the International Digital Humanities Conference (DH).
• Burghardt, M., Lamm, L., Lechler, D., Schneider, M. & Semmelmann, T. (2015). MusicXML Analyzer. Ein Analysewerkzeug für die computergestützte Identifikation von Melodie-Patterns. In Proceedings des 9. Hildesheimer Evaluierungs- und Retrievalworkshops (HiER) (S. 29–42).
• Meier, F., Bazo, A., Burghardt, M. & Wolff, C. (2015). A Crowdsourced Encoding Approach for Handwritten Sheet Music. In J. Roland, Perry; Kepper (Hg.), Music Encoding Conference Proceedings 2013 and 2014 (S. 127–130).

 

In quantitative drama analysis, we use different methods from the fields of NLP and text mining to facilitate a distant reading of stage plays. A particular focus of our work in this area is sentiment analysis.

Publications:

• Schmidt, T., Burghardt, M., Dennerlein, K. & Wolff, C. (2019). Katharsis – A Tool for Computational Drametrics. In Book of Abstracts, DH 2019.
• Schmidt, T., Burghardt, M. & Wolff, C. (2019). Towards Multimodal Sentiment Analysis of Historic Plays: A Case Study with Text and Audio for Lessing’s Emilia Galotti. Proceedings of the DHN (DH in the Nordic Countries) Conference, Copenhagen.
• Schmidt, T. & Burghardt, M. (2018). An Evaluation of Lexicon-based Sentiment Analysis Techniques for the Plays of Gotthold Ephraim Lessing. Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (pp. 139-149). Santa Fe, New Mexico: Association for Computational Linguistics.
• Schmidt, T., Burghardt, M. & Dennerlein, K. (2018). Sentiment Annotation of Historic German Plays: An Empirical Study on Annotation Behavior. Sandra Kübler, Heike Zinsmeister (eds.), Proceedings of the Workshop on Annotation in Digital Humanities (annDH 2018) (pp. 47-52). Sofia, Bulgaria.
• Schmidt, T. & Burghardt, M. (2018). Toward a Tool for Sentiment Analysis for German Historic Plays. In: Piotrowski, M. (ed.), COMHUM 2018: Book of Abstracts for the Workshop on Computational Methods in the Humanities 2018 (pp. 46-48). Lausanne, Switzerland: Laboratoire laussannois d’informatique et statistique textuelle.
• Schmidt, T., Burghardt, M. & Wolff, C. (2018). Herausforderungen für Sentiment Analysis-Verfahren bei literarischen Texten. In: Burghardt, M. & Müller-Birn, C. (Hrsg.), INF-DH-2018. Bonn: Gesellschaft für Informatik e.V.
• Schmidt, T., Burghardt, M. & Dennerlein, K. (2018). “Kann man denn auch nicht lachend sehr ernsthaft sein?” – Zum Einsatz von Sentiment Analyse-Verfahren für die quantitative Untersuchung von Lessings Dramen. In Book of Abstracts, DHd 2018.
• Wilhelm, T., Burghardt, M. & Wolff, C. (2013). “To See or Not to See” - An Interactive Tool for the Visualization and Analysis of Shakespeare Plays. In Tagungsband der Konferenz „Kultur und Informatik“: Visual Worlds & Interactive Spaces (S. 175–185).