Conference "Newspapers, Magazines & AI Models: Training and (Re-)Use in the Digital Humanities"
When: Wednesday, May 7 (start: 14:00) - Thursday, May 8, 2025 (end: 16:00)
Where: Seminar room 1, Campus of the Austrian Academy of Sciences,
Bäckerstraße 13, 1010 Vienna
Registration: Due to limited capacities the organisers are kindly asking to register in advance via the registration form .
Languages: The presentations will be held in either German or English.
Organisation: Department of Literary and Textual Studies , Austrian Centre for Digital Humanities and Cultural Heritage (ACDH-CH), in cooperation with DHd-AG Zeitungen & Zeitschriften
The two-day conference is dedicated to the use of AI models for the digitization and analysis of newspapers and magazines from the early modern period to the present. This covers both the “out-of-the-box” use or fine-tuning of existing models and the training of new models.
The term “AI model” is deliberately defined broadly and includes several subfields of artificial intelligence (e.g., Machine Learning, Deep Learning, Generative AI, NLP) and architectures (e.g., CNNs, BERT, GPT, CLIP) as well as different modalities (text, image, multimodal models) and modes of integration into individual workflows (e.g., through applications such as Transkribus, Newspaper Navigator; through Python libraries like spaCy, flair).
The conference focuses on various application scenarios of AI in relation to newspapers and magazines. The following areas of use are of particular interest:
- Layout analysis and structural annotation
- Automated Text Recognition (HTR, OCR)
- Text genre classification
- Semantic/linguistic annotation (e.g., Named Entity Recognition, Part-of-Speech Tagging)
- Image annotation and classification (Computer Vision)
- Format transformation and data modeling
- Corpus design and searchability
- Data analysis and visualization
Programme
Day 1
| 14:00-14:30 | Welcome and Introduction | Alexandra N. Lenz, Claudia Resch, Nina C. Rastinger |
|---|
Panel 1: Digitizing and enriching newspapers & magazines with AI - I
| 14:30-15:00 | Hierarchical Structure Extraction from Newspaper Images Using a Transformer-Based Model | William Mocaër, Clément Chatelain, Stéphane Nicolas, Thierry Paquet, Tom Simon, Pierrick Tranouez |
|---|---|---|
| 15:00-15:30 | The FINLAM Newspaper Dataset - a dataset for end-to-end newspaper recognition | Solène Tarride |
| 15:30-16:00 | From Image to Machine-Readable text: AI for Layout Analysis, OCR and Post-Correction for Job Ads from Historical Newspapers | Klara Venglarova, Raven Adams, Georg Vogeler |
| 16:00-16:30 | Coffee break |
Panel 2: Digitizing and enriching newspapers & magazines with AI - II
| 16:30-17:00 | Das Darmstädter Tagblatt und zwei KI-Lösungen: Transkribus-Workflows und die Entwicklung eines KI-Assistenten | Dario Kampkaspar, Kevin Kuck, Anna Christina Kupffer |
|---|---|---|
| 17:00-17:30 | Werkstattbericht aus der historisch-kritischen digitalen Edition der „Neuen Zeitschrift für Musik“ 1834-1844 | Nelly Krämer-Reinhardt |
Day 2
Panel 3: Analyzing magazines with AI
| 09:30-10:00 | AI-Driven Analysis of Female Representations in Fin-de-Siècle Spanish Magazines | Adriana Rodríguez-Alfonso |
|---|---|---|
| 10:00-10:30 | Challenges in dealing with historical gossip | Christian Lendl |
| 10:30-11:00 | Potenziale und Herausforderungen einer KI-unterstützten Medien- und Texterschließung am Beispiel der Gattung “Fotogedicht” | Lisa Hufschmidt |
| 11:00-11:30 | Coffee break |
Panel 4: Analyzing magazines & newspapers with AI
| 11:30-12:00 | LexiMus Project. Advantages and Challenges of Artificial Intelligence in the Analysis of Music Press | Daniel Martín Sáez, María Isabel Jiménez Gutiérrez |
|---|---|---|
| 12:00-12:30 | LLM-based list analysis: From semi-structured newspaper texts to structured data | Nina C. Rastinger |
| 12:30-14:00 | Lunch break (catered) |
Panel 5: Analyzing newspapers with AI
| 14:00-14:30 | Semantische Variationen und Bedeutungswandel im Ukrainischen: Herausforderungen für Multilinguale Sprachmodelle | Nataliia Cheilytko |
|---|---|---|
| 14:30-15:00 | Part-of-speech and grammar tagging with German spaCy pipelines from a linguistic perspective: Opportunities and challenges in the annotation of diminutives in forum posts on an Austrian online newspaper article | Katharina Korecky-Kröll |
| 15:00-16:00 | Concluding exchange over coffee and cake |
More information, abstracts and contact details are available on the ACDH-CH website:
Conference "Newspapers, Magazines & AI Models: Training and (Re-)Use in the Digital Humanities"