DE-BIAS: Detecting and contextualizing biased language in metadata
Resource type
Conference paper (unpublished)
Creator (person)
Rose, Kristina
Date published
October 20, 2025
Abstract
Cultural heritage institutions in Europe and beyond have been undertaking work to describe and catalogue the historical objects in their collections for decades. However, once created, catalogue data are rarely updated to reflect changes in language and society. As a result, many object and collection descriptions that once fit into popular social narratives in some cases use language that is offensive, inappropriate or even harmful. The DE-BIAS project developed a tool and frameworks to detect, address and contextualize biassed language in cultural heritage collections' metadata.
Event title
Open and Engaged 2025: Who Owns Our Knowledge?
Publisher
British Library
Official URL
Rights statement
In Copyright
Additional information
The attached files include the slides and recording of this paper and an edited transcript. The transcript can be viewed using a text editor such as Notepad or used for subtitles. Part of the session on Ownership and Access in Cultural Heritage.