Untapped data resources. Applying NER for historical archival records of state authorities

Venla Poso; Tanja Välisalo; Ida Toivanen; Antero Holmila; Jari Ojala

doi:10.5617/dhnbpub.10650

Untapped data resources. Applying NER for historical archival records of state authorities

Authors

Venla Poso
Tanja Välisalo https://orcid.org/0000-0001-8678-4683
Ida Toivanen
Antero Holmila https://orcid.org/0000-0003-2456-7223
Jari Ojala https://orcid.org/0000-0002-4348-8857

DOI:

https://doi.org/10.5617/dhnbpub.10650

Abstract

Archives around the world are digitising their material at a growing speed. The National Archives of Finland launched a mass digitisation process in 2019 aiming to digitise vast amounts of state authority
archives. In order to improve the access and use of this data by researchers, we present the data transfer process of state authority data and the development of named entity recognition (NER) for enriching and using archival data from state authorities. In this process, we have developed two new named entities that are not included in published NER models for the Finnish language. This work is conducted as part of the DARIAH-FI infrastructure.

2023 Conference Proceedings cover image, including title of the conference and a background featuring a painting of the ocean and sky.

Downloads

Published

2023-10-10

How to Cite

Poso, Venla, Tanja Välisalo, Ida Toivanen, Antero Holmila, and Jari Ojala. 2023. “Untapped Data Resources. Applying NER for Historical Archival Records of State Authorities”. Digital Humanities in the Nordic and Baltic Countries Publications 5 (1). Oslo, Norway:55-69. https://doi.org/10.5617/dhnbpub.10650.

Download Citation

Issue

Vol. 5 No. 1 (2023): DHNB2023 Conference Proceedings

Section

Articles

License

This work is licensed under a Creative Commons Attribution 4.0 International License.

This work is licensed under a CC BY 4.0 license.