Digital Publishing for the Humanities: New Technologies and Ideas 

The use of cognitive computing techniques based on Artificial Intelligence for e.g. machine learning-based classification and natural language processing, is making the transcription of sources and annotation of texts easier. Several cutting-edge projects are continuously being developed and made available, however, their outreach and impact is often limited by lack of awareness of such advancements by research groups which, due to the limitations of established collaboration networks, lack of institutional guidance and other factors, miss out on the achievements by fellow scholars.

The aim of this conference is to gather accounts of different experiences with integrating the use of cognitive computing in the production of digital publications - particularly addressing TEI-XML as target format. It is intended as a venue for participants to share their insights into technological improvements, proposals for methodological advancements, innovations in editorial workflows and possibly novel models for them.

Organizing Committee:

• Alessandro Adamou, Bibliotheca Hertziana Max Planck Institute for Art History
• Elisa Bastianello, Bibliotheca Hertziana Max Planck Institute for Art History
• Christine Grundig, Kunsthistorisches Institut & Digital History Lab, University of Zurich

Program:

Day 1: (18/10/2022)

08:45-09:00: Registration

09:00-09:15: Opening speech

• Professor Tristan Weddigen, Elisa Bastianello (Bibliotheca Hertziana – Max Planck Institute for Art History)

09:15-11:15: Session 1

• Simon Gabay (Université de Genève)
  The SegmOnto Project: Standardizing Document Layout Analysis

• Phillip Benjamin Ströbel, Andreas Fischer*, Lukas Fischer & alii (Department of Computational Linguistics, University of Zurich, *University of Applied Sciences, Fribourg)
  Bullinger Digital – From Scans, TUSTEP, PDFs, HTMLs and Text Files to TEI and an Online Search System

• Maxim N. Kupreyev, Polina Solonets* (Goethe-Universität Frankfurt, *Max Planck Institute for Legal History and Legal Theory)
  Waterfall , Agile and DevOps: Advanced Practices for the Large-Scale TEI Editions at the “School of Salamanca” Text Collection

11:15-11:30: coffee break

11:30-13:30: Session 2

• Klaus Thoden, Josefine Wähler, Lars Müller (BBF | Bibliothek für Bildungsgeschichtliche Forschung)
  Transforming the Jahrbuch für Historische Bildungsforschung (JHB) into a TEI-based journal

• Giorgia Agostini (Universities of Florence, Pisa, Siena)
  A Methodological study for the construction of the Ligorio Digital platform: training HTR models

• James M.S. Cowey, Rodney Ast (Universität Heidelberg, Institut für Papyrologie)
  Papyrological Publication Platform (P3)

13:30-14:30: Lunch (only for speakers)

14:30-15:50: Session 3

• Günter Mühlberger, *Sara Mansutti (University of Innsbruck, Digital Humanities Research Centre, *READ COOP-SCE)
  Could Handwritten Text Recognition revolutionise the future of digital editions of primary sources? Transkribus as a platform to facilitate the editorial workflow.

• Dario Kampkaspar (Technische Universität Darmstadt)
  PAGE2TEI - Exporting from Transkribus (or others tools) to TEI

15:50-16:10 coffee break

16:10-18:10: Workshop 1

• Sara Mansutti (READ COOP-SCE)
  Transkribus Intermediate Workshop with hands-on session
  (To fully enjoy the workshop, everyone is advised to bring their own laptop. Before the workshop, please register to Transkribus at this link and prepare a folder with about ten images of handwritten/printed documents on which you would like to apply Transkribus)

Day 2: (19/10/2022)

09:00-09:15: Opening day 2

• Christine Grundig (Kunsthistorisches Institut & Digital History Lab, University of Zurich)

09:15-11:15: Session 4

• Elena Chestnova (Universita della Svizzera italiana)
  Graph-based Digital Edition: Interim Report from the Semper Project

• Emiliano Degl’Innocenti, Carmen Di Meo, Alessia Spadi, Federica Spinelli (Istituto Opera del Vocabolario Italiano – Consiglio Nazionale delle Ricerche)
  Integrating TEI Digital Editions in a Linked Open Data Framework supporting Digital Arts and Humanities & Cultural Heritage Research

• Damiano Delle Fave (University of Rome “La Sapienza”)
  Titi Online Project: the construction of an art-historical lemmary

11:15-11:30: coffee break

11:30-13:30: Session 5

• Silvio Peroni (University of Bologna)
  Towards the availability of FAIR and open citation data

• Reto Baumgartner (University of Zurich)
  Steps to the online publication of “Heinrich Wölfflin – gesammelte Werke”

• Wolfgang Meier (e-editiones)
  TEI Publisher: fast track to an edition

13:30-14:30: Lunch (only for speakers)

14:30-15:30: Session 6

• Christoph Sander (Independent scholar)
  Semantic Image Annotation with Transkribus and ICAT: The Case of Rara Magnetica

• Mike Bennett (Digital Scholarship Developer)
  Semantic Image Annotation with Transkribus and ICAT: The Development Journey

15:30:16:00: coffee break

16:00-18:00: Workshop 2

• Magdalena Turska (e-editiones)
  TEI Publisher: editions with future

If you are planning to attend in person, please send an email to Maria Francesca Bocchi. To join us online register HERE.

The slides from the presentations are available online https://doi.org/10.17617/3.PEJU8B