Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
1Ben-Gurion University of the Negev, Israel; 2Shamoon College of Engineering, Beer-Sheva, Israel; 3The Open University of Israel
Paleographical features can be extracted from digitized images by applying deep machine learning. This paper presents an unsupervised deep-learning method for determining script types and modes for medieval Hebrew manuscripts. The results would be presented vs. the previously published results of supervised deep learning for the same datasets.
Zero-shot keyword spotting, using CLIP for modern manuscripts
Loren Verreyen
University of Antwerp, Belgium
In this presentation, I aim to demonstrate how the recently introduced CLIP-model can be used as a valuable tool to access and analyse digitised manuscripts without the need of providing manual transcriptions first. This entails a shift which would allow the efficient browsing of digital images of any handwritten document.
Documenting Workflows for HTR to TEI Conversions for Cultural Institutions: The Evolving Hands Project
James Cummings1, Diane Jakacki2, Valentina Flex1, Evie Jeffrey1, Carrie Pirmann2, Ian Johnson1, Alexandra Healey1
1Newcastle University, United Kingdom; 2Bucknell University, USA
This proposed short paper will look at the work of the Evolving Hands project which is undertaking three case studies to demonstrate ways TEI-based HTR workflows can be iteratively incorporated into curation by under-resourced cultural institutions. We will present all the case studies but focus on the Gertrude Bell Archive.
“I’m here to fight for ground truth”: HTR-United, a solution towards a common for HTR training data
Alix Chagué1,2, Thibault Clérice3,1
1ALMAnaCH, Inria, France; 2Université de Montréal, Montréal, Canada; 3Centre Jean Mabillon, PSL-Ecole nationales des chartes
The improvement of the automatic transcription of manuscripts relies on an easier access to training data of good quality (ground truth). HTR-United offers a solution to find and document such datasets, potentially creating a common. We present the set-up of this ecosystem and its main outcomes.
Constrained. A Computational Study of the Influence of Formal Characteristics on the Transmission of the Middle Dutch Martijn trilogy by Jacob van Maerlant
Sofie Moors1,2
1University of Antwerp, Belgium; 2FWO Research Foundation - Flanders
This paper investigates to what extent formal aspects, such as rhyme, stanza form, and text structure, might have influenced the medieval copying process. To this end, all 17 manuscripts of Jacob van Maerlant’s Martijn trilogy have been computationally aligned. A first test verified the constraining character of rhyme.
