Mastodawn

Today, our colleague @MahsaVafaie was presenting "End-to-end Information Extraction from Archival Records with Multimodal Large Language Models" at the 34th ACM Int. Conference on Information and Knowledge Management (CIKM 2025) in Seoul, Korea. This is joint work together with Sven Hertling, Inger Banse & Kevin Dubout (BArch), @lysander07

slides: https://zenodo.org/records/17595883
paper: https://dl.acm.org/doi/10.1145/3746252.3761503

#cikm2025 #semanticweb #AI #llms #culturalheritage #digitalhumanities @bmf @fiz_karlsruhe

Mahsa Vafaie Oct 14

Harald Sack Oct 14

Today, I'm at Bundesarchiv in Koblenz for the Strategy & Planning meeting of our project "Wiedergutmachung". Our task in this project is to develop efficient information extraction from historical case files of the German Postwar recompensation process of nationalsocialist injustice.

@fiz_karlsruhe @fizise @LandesarchivBW #bundesarchiv @bmf #knowledgegraphs #llms #AI #informationextraction #archives #project @ddbkultur @archivportal @MahsaVafaie @fschwic

Mahsa Vafaie Oct 10

Harald Sack Oct 10

Open PhD/Junior Researcher Position in Neurosymbolic AI and Information Extraction on historical documents at FIZ Karlsruhe - Knowledge-driven AI research group (former ISE research group), starting at Jan 1, 2026.
Application Deadline: Oct 31, 2025
https://www.fiz-karlsruhe.de/en/stellenanzeigen/phdjunior-researcher-wmx-0

#jobadvertisement #phd #AI #neurosymbolicAI #informationextraction #machinelearning #knmowledgegraphs #ontologies @fiz_karlsruhe @fizise #dh #culturalheritage @nfdi4culture @MahsaVafaie @tabea @sourisnumerique @enorouzi

Mahsa Vafaie Oct 8

Show thread

Ania Jacyszyn Oct 8

@DiTraRe @Feelix @MahsaVafaie @fiz_karlsruhe @KIT_Karlsruhe @ITAS
Check out our presentation on Zenodo: https://zenodo.org/records/17281939

"Streamlining Data Publication: Automatic Metadata and Large Datasets in the Age of AI." Discussion Session at Open Science Conference 2025

This is a presentation of the discussion session "Streamlining Data Publication: Automatic Metadata and Large Datasets in the Age of AI" created by the DiTraRe team for the Open Science Conference in Hamburg 2025. Research data repositories are essential infrastructure for enabling Open Science and ensuring data is Findable, Accessible, Interoperable, and Reusable (FAIR). However, researchers working on repositories face significant challenges in handling ever-increasing volumes of large datasets and the often time-consuming manual process of creating comprehensive, quality metadata. These issues can hinder data publication workflows and limit the findability and usability of valuable research output. We will present the challenges encountered, propose solutions and first implementations for automatic metadata extraction and large data handling, and discuss how these innovations contribute to a more streamlined and scalable data publication workflow. Participants will have the opportunity to engage with developers and users of repositories, explore the practical implications for their own data management practices, and discuss the potential for adopting similar solutions in other repository contexts. This discussion session will provide insights into the approaches, technologies, and lessons learned from the Leibniz Science Campus “Digital Transformation of Research” (DiTraRe) work on RADAR and implementation of AI methods in the topic of metadata standardisation. The session is especially relevant for everyone interested in the practical implementation of advanced research data management features that promote reproducibility, efficiency and FAIR principles.

Zenodo

Mahsa Vafaie May 21, 2025

FIZ KDAI Research Group May 21, 2025

Today, our team member @MahsaVafaie was presenting her work on MLLM-based Information Extraction "Multimodal Large Language Modelle und die Bundeszentralkartei für Entschädigungsverfahren. Ein KI-Projekt im Themenportal "Wiedergutmachung nationalsozialistischen Unrechts"" at 29. Archivwissenschaftliches Kolloquium "AI in the Archives – Are We on the Brink of a Revolution?" in Marburg

https://www.archivschule.de/DE/forschung/archivwissenschaftliche-kolloquien/29-archivwissenschaftliches-kolloquium.html

#dh #digitalhumanitites #llm @fiz_karlsruhe @LandesarchivBW @bmf #AI #archives

29. Archivwissenschaftliches Kolloquium

Mahsa Vafaie May 17, 2025

FIZ KDAI Research Group May 17, 2025

This Saturday & Sunday, we will present our research in the Wiedergutmachung BMF project at the EFFEKTE 2025 science festival in Karlsruhe in front of the city palace. If you happen to be there and see us, just say "Hi" ;-)

We will present the challenges & opportunities of opening up (digitalising) archival documents for research...

https://effekte.karlsruhe.de/

@LandesarchivBW @dfaehle @bmf @fiz_karlsruhe @lysander07 @MahsaVafaie #digitalisation #events #effekte2025 @KIT_Karlsruhe

EFFEKTE

Einstieg zum Wissenschaftsfestival und zur Wissenschaftsreihe "EFFEKTE" der Stadt Karlsruhe.

Mahsa Vafaie May 17, 2025

Harald Sack May 17, 2025

Explaining interested people in Karlsruhe about our research on the challenges & opportunities of the digitalisation of the more than 100km of archival documents of the recompensation process of nationalsocialist injustice

#digitalisierung @bmf @fiz_karlsruhe @fizise @MahsaVafaie @LandesarchivBW

Mahsa Vafaie May 15, 2025

FIZ KDAI Research Group May 15, 2025

Last week our colleague Mahsa Vafaie gave a presentation on "National Socialist Injustice on the Semantic Web - From archival documents to a knowledge graph" at the Open Research Colloquium Digital History" at Humboldt-Universität zu Berlin. Now, the youtube video is available at:
https://www.youtube.com/watch?v=ZDB_VeZXtI8

#wiedergutmachung @bmf @LandesarchivBW @MahsaVafaie @GenAsefa @lysander07 @fiz_karlsruhe #dh #digitalhistory @cliotex @NFDI4Memory @nfdi4culture

Mahsa Vafaie: National Socialist Injustice on the Semantic Web

This presentation was part of the "Open Research Colloquium Digital History" at Humboldt-Universität zu Berlin, held on May 7, 2025. Mahsa Vafaie (FIZ Karlsr...

YouTube

Mahsa Vafaie May 7, 2025

FIZ KDAI Research Group May 7, 2025

Today (16:15–17:45 CEST), in the series of the open Digital History research colloquium at HU Berlin, co‑hosted with NFDI4Memory, our colleague Mahsa Vafaiewill present her work on the digital processing of millions of post‑war compensation files using cutting‑edge methods in the project Wiedergutmachung:

Abstract & access: https://dhistory.hypotheses.org/10161

#dh #llms @NFDI4Memory @nfdi4culture @fiz_karlsruhe @lysander07 @MahsaVafaie

Mahsa Vafaie: National Socialist Injustice on the Semantic Web: From Archival Records to a Knowledge Graph

The project “Wiedergutmachung nationalsozialistischen Unrechts” (eng. “Reparations for National Socialist Injustice”), funded by the Federal Ministry of Finance (BMF), aims to provide centralised, structured and comprehensive digital access to documents and data sources from the context of reparations for injustices committed under National Socialism in Germany. The resulting thematic portal addresses a broad and diverse … „Mahsa Vafaie: National Socialist Injustice on the Semantic Web: From Archival Records to a Knowledge Graph“ weiterlesen

Digital History Berlin

Mahsa Vafaie Apr 24, 2025

FIZ KDAI Research Group Apr 24, 2025

Our colleague @MahsaVafaie held yesterday a presentation about the WIedergutmachung project on Separation of hand-written and machine-written text in archival documents at the Stuttgart AI, Machine Learning and Computer Vision Meetup.

#digitalhumanities #dh #AI #cv #computervision @LandesarchivBW @fiz_karlsruhe @lysander07 @bmf #wiedergutmachung #archives #holocaust