@inbook{ec65c294464f45589e110d4f06ca6a07,
title = "Recognising and linking entities in old dutch text: A case study on voc notary records",
abstract = "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{\textquoteright}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.",
keywords = "Domain adaptation, Maritime history, Named entity recognition",
author = "Barry Hendriks and Paul Groth and {van Erp}, Marieke",
note = "Publisher Copyright: Copyright {\textcopyright} 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).",
year = "2021",
language = "English",
volume = "2810",
series = "CEUR Workshop Proceedings",
publisher = "CEUR Workshop Proceedings",
pages = "25--36",
booktitle = "COLCO 2020 ",
}