Research Position: NLP Metadata Enrichment of Museum Texts (all genders welcome)

An der Georg-August-Universität Göttingen Stiftung Öffentlichen Rechts – Institut für Informatik ist ab dem eine Stelle als Research Position: NLP Metadata Enrichment of Museum Texts (all genders welcome). Entgeltgruppe 13 TV‑L - in Vollzeit (teilzeitgeeignet) zu besetzen. Die Stelle ist befristet bis .

The Chair of Scientific Information Analytics, headed by Prof. Dr. Bela Gipp (GippLab — conducts research at the intersection of computer science, data science, and information science. Natural language processing (NLP) based on Large Language Models (LLM) is a particular research focus of the chair. As part of the research project "AI in Museums", we are looking for one full‑time position for PhD researchers (all genders welcome). The job posting is subject to the confirmation of project funding.

Project Description

Millions of objects in museums hold untapped knowledge, yet their histories remain locked in uncataloged collections and unstructured texts. The KIM consortium aims to change this by deploying AI to transform how museums manage and share knowledge. The project tackles three core challenges:

• Provenance Research: AI‑assisted reconstruction of artifact ownership histories.
• Cataloging Support: Tools that accelerate expert cataloging, e.g., via visual similarity search.
• Metadata Enrichment (your focus): Automatic completion and semantic enrichment of museum object metadata using information extracted from scientific publications, excavation reports, and digital editions.

Your work at Göttingen will lead the metadata enrichment stream and deliver a demonstrable proof‑of‑concept on the University of Göttingen’s Virtual Museum (VIAMUS) collection of ancient sculptures. You will be part of a collaborative consortium including Göttingen partners and external institutions such as the VZG (GBV Union Catalogue), TIB Hannover, and Leuphana University Lüneburg, working closely with museum professionals, librarians, and domain scholars. The job posting is subject to the confirmation of project funding.

Your Responsibilities

• Conduct cutting‑edge research in domain‑adapted NLP for cultural‑heritage texts.
• Design and train specialized Transformer‑based language models for museum metadata enrichment.
• Develop methods to extract object characteristics and relations from heterogeneous sources (scientific articles, excavation reports, digital editions).
• Fine‑tune models for Named Entity Recognition/Extraction (NER), Relation Extraction, and Question Answering on domain‑specific corpora.
• Deliver a Proof‑of‑concept by enriching metadata for the VIAMUS database (ancient sculptures).
• Collaborate with consortium partners to integrate models into a sustainable MLOps pipeline for real‑world museum use.
• Publish in leading venues (e.g., ACL, EMNLP, NAACL) and present results to stakeholders in the GLAM (Galleries, Libraries, Archives, Museums) community.
• Teach and co‑supervise B.Sc./M.Sc. students in related topics.

Your Profile

• A Master’s degree (or equivalent) with a "very good" grade in Computer Science, Computational Linguistics, Data Science, or a closely related field.
• Strong Python skills and practical experience with PyTorch and Hugging Face.
• Solid foundation in NLP downstream tasks (e.g., tokenization, NER, word sense disambiguation), neural networks, and basic linguistics.
• Familiarity with information extraction and working with unstructured/heterogeneous texts; experience with cultural‑heritage data is a plus.
• Professional proficiency in German and English (C1 level, written and spoken).

We Offer

• A stimulating, interdisciplinary research environment at a leading German university.
• The opportunity to shape next‑generation AI tools that make cultural heritage more accessible for research and society.
• Close, supportive doctoral supervision and collaboration with experts from museums, libraries, and academia.
• Integration of your research into a production‑oriented MLOps pipeline used by partner institutions.
• Opportunities to publish and present at premier international conferences and GLAM venues.
• A full‑time position with conditions according to university and public‑funding regulations; part‑time arrangements are possible by agreement.
• Office space and technical equipment.
• The position will be located in Göttingen on‑site.

Die Universität Göttingen strebt in den Bereichen, in denen Frauen unterrepräsentiert sind, eine Erhöhung des Frauenanteils an und fordert daher qualifizierte Frauen nachdrücklich zur Bewerbung auf. Sie versteht sich zudem als familienfreundliche Hochschule und fördert die Vereinbarkeit von Wissenschaft/Beruf und Familie. Der berufliche Teilhabe von schwerbehinderten Beschäftigten sieht sich die Universität in besondere Weise verpflichtet und begrüßt deshalb Bewerbungen schwerbehinderter Menschen. Bei gleicher Qualifikation erhalten Bewerbungen von Menschen mit Schwerbehinderung den Vorzug. Eine Behinderung bzw. Gleichstellung ist zur Wahrung der Interessen bereits in die Bewerbung aufzunehmen.

Bitte reichen Sie Ihre aussagekräftige Bewerbung mit allen wichtigen Unterlagen bis zum ausschließlich über das Bewerbungsportal erteilt Herr Jan Philip Wahle, E-Mail: , Tel. .

Hinweis: Wir weisen darauf hin, dass die Einreichung der Bewerbung eine datenschutzrechtliche Einwilligung in die Verarbeitung Ihrer Bewerbungsdaten durch uns darstellt. Näheres zur Rechtsgrundlage und Datenverwendung finden Sie im Hinweisblatt zur Datenschutzgrundverordnung (DSGVO).

#J-18808-Ljbffr