• Digital Humanities and Cultural Heritage
• Publications close
• Research data close
• Other research products close
• Conference object close
• Zurich Open Repository and Archive close
• OpenAIRE close
• BMC Bioinformatics close

"Anhand des Briefwechsels Heinrich Bullingers (1504-1575), das rund 10'000 Briefe umfasst, demonstrieren wir den Stand der Forschung in automatisierter Handschriftenerkennung. Es finden sich mehr als hundert unterschiedliche Schreiberhände in den Briefen mit sehr unterschiedlicher Verteilung. Das Korpus ist zweisprachig (Latein/Deutsch) und teilweise findet der Sprachwechsel innerhalb von Abschnitten oder gar Sätzen statt. Auf Grund dieser Vielfalt eignet sich der Briefwechsel optimal als Testumgebung für entsprechende Algorithmen und ist aufschlussreiche für Forschungsprojekte und Erinnerungsinstitutionen mit ähnlichen Problemstellungen. Im Paper werden drei Verfahren gegeneinander gestellt und abgewogen. Im folgenden werde drei Ansätze an dem Korpus getestet, die Aufschlüsse zum Stand und möglichen Entwicklungen im Bereich der Handschriftenerkennung versprechen. Erstens wird mit Transkribus eine etablierte Plattform genutzt, die zwei Engines (HTR+ und PyLaia) anbietet. Zweitens wird mit Hilfe von Data Augmentation versucht die Erkennung mit der state-of-the-art Engine HTRFlor zu verbessern und drittens werden neue Transformer-basierte Modelle (TrOCR) eingesetzt." Ein Beitrag zur 9. Tagung des Verbands "Digital Humanities im deutschsprachigen Raum" - DHd 2023 Open Humanities Open Culture.

Multi-task learning (MTL) aims at achieving a better model by leveraging data and knowledge from multiple tasks. However, MTL does not always work – sometimes negative transfer occurs between tasks, especially when aggregating loosely related skills, leaving it an open question when MTL works. Previous studies show that MTL performance can be improved by algorithmic tricks. However, what tasks and skills should be included is less well explored. In this work, we conduct a case study in Financial NLP where multiple datasets exist for skills relevant to the domain, such as numeric reasoning and sentiment analysis. Due to the task difficulty and data scarcity in the Financial NLP domain, we explore when aggregating such diverse skills from multiple datasets with MTL can work. Our findings suggest that the key to MTL success lies in skill diversity, relatedness between tasks, and choice of aggregation size and shared capacity. Specifically, MTL works well when tasks are diverse but related, and when the size of the task aggregation and the shared capacity of the model are balanced to avoid overwhelming certain tasks. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, Volume 1: Long Papers ISBN:978-1-959429-72-2

Handwritten Text Recognition engines play a pivotal role in transforming historical handwritten documents into machine‐readable formats, facilitating efficient access and analysis of invaluable information. We present a comprehensive evaluation of cutting‐edge Handwritten Text Recognition engines, including PyLaia, IDA, and TrOCR. The study aims to assist researchers in making informed decisions for datafication of historical documents. We ensure a fair comparison of the engine performance by utilizing diverse datasets comprising varying languages, scripts, complexities, and historical periods. As a benchmark for improvement, we incorporate datasets previously processed with Transkribus/CitLab HTR+, allowing us to assess the engines' recognition accuracy. By analysing the Character Error Rate (CER), we evaluate their performance.

Both the current upgrades to accelerator-based HEP detectors (e.g. ATLAS, CMS) and also future projects (e.g. CEPC, FCC) feature large-area silicon-based tracking detectors. We are investigating the feasibility of using CMOS foundries to fabricate silicon radiation detectors, both for pixels and for large-area strip sensors. A successful proof of concept would open the market potential of CMOS foundries to the HEP community, which would be most beneficial in terms of availability, throughput and cost. In addition, the availability of multi-layer routing of signals will provide the freedom to optimize the sensor geometry and the performance, with biasing structures implemented in poly-silicon layers and MIM-capacitors allowing for AC coupling. A prototyping production of strip test structures and RD53A compatible pixel sensors was recently completed at LFoundry in a 150nm CMOS process. This presentation will focus on the characterization of pixel modules, studying the performance in terms of charge collection, position resolution and hit efficiency with measurements performed in the laboratory and with beam tests. We will report on the investigation of RD53A modules with 25x100 μm2 cell geometry. Journal of Physics: Conference Series, 2374 (1) ISSN:1742-6596 ISSN:1742-6588