Heritage programs transformed into structured linked data for performing arts
From Show Programs to Linked Data
Information Retrieval
Summary
Lots of old show programs from theaters are hard to find and not scanned into computers yet. The authors show a way to turn these paper programs into neat, digital data that computers can understand easily. They use smart tools that read images and text, organize the information carefully using a special system for art and performance, and check their work to avoid mistakes. By doing this with programs from a famous French festival, they prove the method works well and could help people study performing arts history more easily in the future.
What this means in practice
- •For library digital teams: Automatically convert large heritage show program collections into searchable, interconnected data for better access and preservation.
- •For performing arts archives: Create detailed, interoperable digital catalogs of performing artists and festivals using linked data from historical programs.
Tested on one dataset.
Authors
Clarisse Bardiot, Bernard Jacquemin, Jacob Hart, George Bruseker, Antonios Lagarias, Pierre-Carl Langlais, Brandon Farnsworth, Jeanne Fras
Abstract
Many heritage institutions hold extensive collections of show programs. Too numerous to be cataloged individually, they remain difficult to access and are still largely undigitized. This paper presents a workflow for transforming such documents into structured, interoperable data by combining vision-language models (VLMs), a custom extension of the Linked Art ontology for the performing arts, and different approaches for automatic semantic data annotation. Using the Festival d'Avignon programs (1947--present), preserved at the Biblioth{è}que nationale de France, as a case study, we demonstrate how VLMs achieve more than 98% text transcription accuracy from heterogeneous heritage document images and how constraining large language model generation through a knowledge graph significantly reduces hallucinations in semantic annotation. We argue that this workflow opens new possibilities for large-scale, interoperable performing arts historiography, including the creation of catalogues raisonn{é}s for performing artists, a form of scholarship common in visual arts but absent in performing arts studies.