Art archives are a rich source of information for various reasons: they can proof provenence of certain art pieces, they can help in art history research, and they help in understanding the artist and the context in which he or she was working. These archives contain typically all kinds of heterogeneous documents: auction catalogs, personal correspondence, books, exhibition catalogs, bills, certificates, studies, theses, etc. Many of these archives are not easily accessible, e.g. because they are not yet digitalized. And the one that are digitalized are hard to explore with general text mining tools.
In this project we aim at facilitating access to a large collection of art related documents. To this end we need to adapt standard NLP tools for work in the art domain. The ultimate goal is to generate a knowledge graph which can be easily explored by art historians. The knowlege graph should also serve as a backbone for semantic search functionality and for new ways to represent art entities, e.g. as embeddings in a high dimensional space. Modern deep learning methods will be developed to manage and visualize large collections of art historical and scholarly documents.