Recognising and linking entities in old dutch text: A case study on voc notary records

Barry Hendriks, Paul Groth, Marieke van Erp

Onderzoeksoutput: Hoofdstuk in boek/boekdeelBijdrage aan conferentie proceedingsWetenschappelijkpeer review

Samenvatting

The increased availability of digitised historical archives allows researchers to discover detailed information about people and companies from the past. However, the unconnected nature of these datasets presents a non-trivial challenge. In this paper, we present an approach and experiments to recognise person names in digitised notary records and link them to their job registration in the Dutch East India company’s records. Our approach shows that standard state-of-the-art language models have difficulties dealing with 18th century texts. However a small amount of domain adaption can improve the connection of information on sailors from different archives.

Originele taal-2Engels
TitelCOLCO 2020 
SubtitelCollect and Connect : Archives and Collections in a Digital Age 2020. Proceedings of the International Conference Collect and Connect: Archives and Collections in a Digital Age Leiden, the Netherlands, November 23-24, 2020.
UitgeverijCEUR Workshop Proceedings
Pagina's25-36
Aantal pagina's12
Volume2810
StatusGepubliceerd - 2021

Publicatie series

NaamCEUR Workshop Proceedings
UitgeverijCEUR Workshop Proceedings
ISSN van geprinte versie1613-0073

Vingerafdruk

Duik in de onderzoeksthema's van 'Recognising and linking entities in old dutch text: A case study on voc notary records'. Samen vormen ze een unieke vingerafdruk.

Citeer dit