Building a VOCabulary: the uses and challenges of thesauri for working with early modern recognized entities

Activity: Talk or presentationAcademic

Description

The GLOBALISE project aims to unlock the extensive archives of the Dutch East India Company (VOC) using Handwritten Text Recognition and Natural Language Processing techniques. By creating a hierarchical reference thesaurus, the project makes the VOC archives researchable and enhances search capabilities. The reference data provides unique identifiers for terms, catalogues their variations and tries to link them to existing definitions where possible. Providing such a contextually appropriate and expandable vocabulary allows researchers to explore the archive with the help of synonyms and related concepts.
Period01 Jun 2023
Event titleDHBenelux 2023
Event typeConference
LocationBrussels, BelgiumShow on map

Keywords

  • Dutch East India Company (VOC)
  • Linked Open Data