#informationextraction — Public Fediverse posts

Sehr schöne Präsentation zu automatischer Metadatenextraktion aus einem Korrespondenzkorpus von Sabrina Strutz (Graz).

Sorgfältige Arbeit/Evaluation mit kritischer Durchsicht der GT Daten (welche Informationen stecken aus der Printedition da drin, die aber aus dem Brief gar nicht entnommen werden können?), Aufschlüsselung von Ergebnisqualität nach Task (Autor-/Ortserkennung) und Phase (Erzeugung von Kandidaten und Bestimmung des endgültigen Vorschlags).

Qwen3-14B-Q6 als lokales Modell zwar schlechter als Sonnet 4.6 (welches sehr gute Ergebnisse liefert, aber auch am teuersten ist) und GPT 5.2, aber auch keine ganz schlechten Ergebnisse. (Und besser mit abgeschaltetem Reasoning!)

Alle Modelle haben Probleme, Schreibeorte aus dem Text zu erschließen, wenn sie nicht in der Datumszeile genannte werden.

#DHd2026 #InformationExtraction #LLM

🤖🔧 Apparently, structured outputs are the latest "sliced bread" of #AI, but turns out they're just fancy-shmancy wrappers that make your LLM dumber than a bag of hammers 🤦‍♂️. Who knew that squeezing responses into neat little boxes could actually lead to a train-wreck of information extraction? 🚂💥
https://boundaryml.com/blog/structured-outputs-create-false-confidence #Innovation #AI #Limitations #LLMs #InformationExtraction #TechHumor #StructuredOutputs #HackerNews #ngated

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

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

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

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

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

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

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

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

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

Today, the 2nd lecture of #ISE2025 took place with an introduction into Natural Language Processing, which will be subject of our lecture for the next 4 weeks.

#AI #nlp #informationextraction #ocr #ner #linguistics #computationallinguistics #morphology #pos #ambiguity #language @fiz_karlsruhe @fizise @tabea @enorouzi @sourisnumerique #AIart #generativeAI #machinetranslation #languagemodels #llm

Our colleague Hidir Arras from patent4science research is co-organizing the 6th PatentSemTech Workshop at #SIGIR2025 in the beautiful city of Padua, Italy! Call for Papers is open 'til April 23: http://ifs.tuwien.ac.at/patentsemtech/

Submit your cutting-edge research, case studies, and demos exploring #AI, #NLP, and #TextMining innovations applied to #IP and related domains.

@fiz_karlsruhe #informationextraction #datamining #ir

We currently have two fully-funded open PhD positions in our group with a focus on #NLProc, #InformationExtraction and #TextGeneration. I can really recommend both the group as well as Philipp Cimiano as a supervisor, so take this opportunity!

NLP/Text Generation
EN: https://uni-bielefeld.hr4you.org/job/view/4054
DE: https://uni-bielefeld.hr4you.org/job/view/4053

NLP/Information Extraction
EN: https://uni-bielefeld.hr4you.org/job/view/4059
DE: https://uni-bielefeld.hr4you.org/job/view/4057

If you have any questions, do not hesitate to contact me or Philipp directly!

ReadMe2KG: Github ReadMe to Knowledge Graph #Challenge has been published as part of the Natural Scientific Language Processing and Research Knowledge Graphs #NSLP2025 workshop co-located with #eswc2025. This #NER task aims to complement the NDFI4DataScience KG via information extraction from GitHub README files.

task description: https://nfdi4ds.github.io/nslp2025/docs/readme2kg_shared_task.html
website: https://www.codabench.org/competitions/5396/

@eswc_conf @GenAsefa @shufan @NFDI4DS #NFDIrocks #knowledgegraphs #semanticweb #nlp #informationextraction

ReadMe2KG: Github ReadMe to Knowledge Graph #Challenge has been published as part of the Natural Scientific Language Processing and Research Knowledge Graphs #NSLP2025 workshop co-located with #eswc2025. This #NER task aims to complement the NDFI4DataScience KG via information extraction from GitHub README files.

task description: https://nfdi4ds.github.io/nslp2025/docs/readme2kg_shared_task.html
website: https://www.codabench.org/competitions/5396/

@eswc_conf @GenAsefa @shufan @NFDI4DS #NFDIrocks #knowledgegraphs #semanticweb #nlp #informationextraction

ReadMe2KG: Github ReadMe to Knowledge Graph #Challenge has been published as part of the Natural Scientific Language Processing and Research Knowledge Graphs #NSLP2025 workshop co-located with #eswc2025. This #NER task aims to complement the NDFI4DataScience KG via information extraction from GitHub README files.

task description: https://nfdi4ds.github.io/nslp2025/docs/readme2kg_shared_task.html
website: https://www.codabench.org/competitions/5396/

@eswc_conf @GenAsefa @shufan @NFDI4DS #NFDIrocks #knowledgegraphs #semanticweb #nlp #informationextraction

ReadMe2KG: Github ReadMe to Knowledge Graph #Challenge has been published as part of the Natural Scientific Language Processing and Research Knowledge Graphs #NSLP2025 workshop co-located with #eswc2025. This #NER task aims to complement the NDFI4DataScience KG via information extraction from GitHub README files.

task description: https://nfdi4ds.github.io/nslp2025/docs/readme2kg_shared_task.html
website: https://www.codabench.org/competitions/5396/

@eswc_conf @GenAsefa @shufan @NFDI4DS #NFDIrocks #knowledgegraphs #semanticweb #nlp #informationextraction

ReadMe2KG: Github ReadMe to Knowledge Graph #Challenge has been published as part of the Natural Scientific Language Processing and Research Knowledge Graphs #NSLP2025 workshop co-located with #eswc2025. This #NER task aims to complement the NDFI4DataScience KG via information extraction from GitHub README files.

task description: https://nfdi4ds.github.io/nslp2025/docs/readme2kg_shared_task.html
website: https://www.codabench.org/competitions/5396/

@eswc_conf @GenAsefa @shufan @NFDI4DS #NFDIrocks #knowledgegraphs #semanticweb #nlp #informationextraction

Our colleague @MahsaVafaie is presenting at the #ISWC2024 Doctoral Consortium her work on "German National Socialist Injustice on the #SemanticWeb: from archival records to a knowledge graph"

presentation: https://zenodo.org/records/14070332

@fiz_karlsruhe #PhD #knowledgegraphs #digitalhumanities #dh #AI @LandesarchivBW #iswc #ocr #informationextraction #llms @bmf

Today I' attending the @Textplus #TextplusPlenary2024 at Schloss Mannheim @unimannheim
I will present a poster about our work on #InformationExtraction from tables in old German magazines.

GOT (General OCR Theory) is a 580M end-to-end OCR-2.0 model now on Hugging Face 🤗

"GOT consists of a Vision-Encoder to convert images into transformers images into tokens and a decoder for generating OCR outputs in various formats (e.g., plain text, markdown, Mathpix). GOT is designed to handle complex tasks like sheets, formulas, and geometric shapes."

Model: https://huggingface.co/ucaslcl/GOT-OCR2_0
GitHub: https://github.com/Ucas-HaoranWei/GOT-OCR2.0/
paper: https://arxiv.org/abs/2409.01704

#ocr #transformers #informationextraction #ai

Yesterday after the successful PhD defense of Nicolas Heist at University of Mannheim together with Chris Bizer and Heiko Paulheim. Congratulations Dr. Nico!

Thesis title: Exploiting semi-structured information in Wikipedia for Knowledge Graph Construction
https://www.uni-mannheim.de/dws/news/nicolas-heist-defended-his-thesis/

#knowledgegraphs #wikipedia #dbpedia #informationextraction #llms @fiz_karlsruhe @fizise @KIT_Karlsruhe

Nice overview about LLMs for data annotation including paper references of papers with open source code & data.
Zhen Tan et al, Large Language Models for Data Annotation: A Survey, https://arxiv.org/abs/2402.13446

#llms #generativeai #informationextraction #dataannotation

Information Service Engineering is the denomination of our research group at @fiz_karlsruhe as well as of my chair at @KIT_Karlsruhe
...and this is how #Midjourney imagines how "Information Service Engineering" might look like ;-)

Our research focus lies on on #knowledgegraphs
#informationextraction
#knowledgeengineering
#ontologies #researchdatamanagement
#exploratorysearch #semanticsearch
#nlp #aiart #generativeai @sourisnumerique @tabea @sashabruns @MahsaVafaie @enorouzi

5 AI tools for summarizing a research paper - Unlock the power of AI tools to extract key insights and condense... - https://cointelegraph.com/news/5-ai-tools-for-summarizing-a-research-paper #researchpapersummarization #condensinginformation. #informationextraction #keyinsights #quillbot #scispacy #aitools #chatgpt

#ConferencePaper for #JCDL22 in Cologne

"A #Library Perspective on Nearly-Unsupervised #InformationExtraction Workflows in #DigitalLibraries"

by Hermann Kroll, Jan Pirklbauer, Florian Plötzky, Wolf-Tilo Balke

https://doi.org/10.48550/arXiv.2205.00716

#JointConferenceOnDigitalLibraries
#JCDL2022

#ConferencePaper for #JCDL22 in Cologne

"A #Library Perspective on Nearly-Unsupervised #InformationExtraction Workflows in #DigitalLibraries"

by Hermann Kroll, Jan Pirklbauer, Florian Plötzky, Wolf-Tilo Balke

https://doi.org/10.48550/arXiv.2205.00716

#JointConferenceOnDigitalLibraries
#JCDL2022

5 AI tools for summarizing a research paper - Unlock the power of AI tools to extract key insights and condense... - https://cointelegraph.com/news/5-ai-tools-for-summarizing-a-research-paper #researchpapersummarization #condensinginformation. #informationextraction #keyinsights #quillbot #scispacy #aitools #chatgpt

5 AI tools for summarizing a research paper - Unlock the power of AI tools to extract key insights and condense... - https://cointelegraph.com/news/5-ai-tools-for-summarizing-a-research-paper #researchpapersummarization #condensinginformation. #informationextraction #keyinsights #quillbot #scispacy #aitools #chatgpt

5 AI tools for summarizing a research paper - Unlock the power of AI tools to extract key insights and condense... - https://cointelegraph.com/news/5-ai-tools-for-summarizing-a-research-paper #researchpapersummarization #condensinginformation. #informationextraction #keyinsights #quillbot #scispacy #aitools #chatgpt