The AI:CULT project is looking for 2 PhD students to develop methods and techniques for applying AI to subjective and polyvocal data sets. The reasons for certain heritage data to be preserved, its interpretation throughout time, and the way heritage data is accessed after digitalisation is all subject to biases. The inherent richness, subjectivity and polyvocal nature of cultural heritage data limits and often even rules out the responsible use of AI. How do we model that “Seventeenth Century” and “The Golden Age” refer to the same era, yet are not fully synonymous and carry different semantic payloads? Current state-of-the-art AI cannot deal with subtleties in a way that does justice to the important role of the heritage institute as a trusted source of information. A crucial question is how can we reap the benefits of AI while guarding against its undesired consequences?

AI:CULT addresses two case studies: 1) automatic analysis and enrichment of object-level descriptions and 2) the creation of data stories from raw collection data. Bias detection and filtering methods will be developed that will be directly tested on the heritage partners’ workflows and made available to all memory organisations in the Netherlands.

More details on the project and how to apply at: https://www.academictransfer.com/en/294803/phd-researchers-humanities-cluster-knaw-amsterdam/

Deadline: 1 November 2020