New collaboration develops AI for cultural heritage

CWI starts a new collaboration around artificial intelligence with heritage and research institutions. In the Cultural AI Lab they will jointly explore the possibilities of AI for cultural research and raise AI’s awareness of the cultural context.

Publication date
16 Nov 2020

CWI starts a new collaboration with heritage and research institutions around artificial intelligence (AI). In the Cultural AI Lab they will jointly explore the possibilities of AI for cultural research and raise AI’s awareness of the cultural context.

Paintings, manuscripts, photographs, videos, newspaper articles - heritage institutions have an enormous wealth of digitized collections. Artificial Intelligence (AI) plays an important role in analyzing these collections and making them accessible. CWI, the KNAW Humanities Cluster, the Dutch National Library, the Netherlands Institute for Sound and Vision, the Rijksmuseum, TNO, the University of Amsterdam and the Vrije Universiteit Amsterdam therefore join forces in the Cultural AI Lab.

Together they will use the possibilities of AI for cultural research and make AI technology aware of the cultural context. The research within the lab aims to make AI technology more aware of cultural contexts and also to align cultural institutions with state-of-the-art AI research in the Netherlands.

Five research projects
The parties will work closely together to develop AI tools that can be applied in the cultural heritage sector. In the coming months, the first five research projects will start, including an investigation into the automatic tracing of colonial terminology in collection data and an investigation into framing in online journalism.

Multiple perspectives on heritage
“The collaboration also opens up possibilities to investigate how AI can help to map out multiple perspectives on heritage”, says Laura Hollink, researcher at the CWI. “Our goal is to be able to create AI systems in the future that can deal with the rich, subjective, polyphonic data from the cultural heritage sector.”

Cultural AI
The lab builds a bridge between cultural heritage institutions, humanities and computer science. Data and information from relevant heritage institutions and technical knowledge from research institutes form the basis for the development of AI tools that do justice to the complexity of human culture and can be applied within the cultural heritage sector in the Netherlands. All research projects within the lab are related to this.

Current and future research within the Cultural AI initiative will be divided among the institutions involved. PhD students and postdocs will initially spend four years working on research within the heritage institutions involved.

The Cultural AI Lab will start with five research projects:

<u>AI:CULT Culturally Aware
</u>Automated analysis and enrichment of object descriptions in museum collections using AI. The goal is to use artificial intelligence within the cultural heritage in a transparent and inclusive way, while keeping the user in control and providing insight into changes made inspired by AI research.
KNAW Meertens Institute, CWI, KNAW Humanities Cluster, Netherlands Institute for Sound and Vision and Dutch National Library. Funded by the Dutch Research Council.

<u>SABIO - the SociAl Bias Observatory
</u>Automated analysis of collection descriptions in museum collections in order to detect colonial terminology. This research maps the cultural bias in collections and updates the information without overwriting existing collection data.
KNAW Humanities Cluster, Museum of World Cultures, Netherlands Institute for Sound and Vision and Dutch National Library. Funded by Network Digital Heritage

<u>Better Informing Citizens about Current Debates
</u>Automated analyses of contemporary debates in the press with the aim of developing a tool that makes it possible to evaluate and improve the quality of online debates.
KNAW Humanities Cluster and Tilburg University

<u>RE-FRAME
</u>Analysis of context and framing in online journalism. In RE-FRAME we investigate the reuse of resources and the role they play in the construction of audio-visual journalistic storytelling through content analysis and (action-based) production analysis. We investigate how new technologies, such as Automatic Speech Recognition and Computer Vision, contained in the CLARIAH Media Suite, can play a role in finding and interpreting content and in journalistic practice.
Utrecht University and Netherlands Institute for Sound and Vision

<u>Researcher in Residence Programme Cultural AI
</u>External researchers can use the data from the Dutch National Library to propose research on the themes of the Cultural AI Lab. The selected researchers will receive compensation and can make use of the facilities of the library during their research. In 2021, the library will collaborate with researcher Simon Kemper (Leiden University) on a project to locate entities (persons, places and organizations) in the multilingual colonial digitized newspapers using various AI language models.