Unsilencing colonial archives via automated entity recognition

Abstract

PurposeThis paper aims to expand the scope and mitigate the biases of extant archival indexes.Design/methodology/approachThe authors use automatic entity recognition on the archives of the Dutch East India Company to extract mentions of underrepresented people.FindingsThe authors release an annotated corpus and baselines for a shared task and show that the proposed goal is feasible.Originality/valueColonial archives are increasingly a focus of attention for historians and the public, broadening access to them is a pressing need for archives.