Published June 5, 2024
| Version v2
Presentation
Open
Accessing the Republic. Entity extraction from the resolutions of the Dutch States-General.
Creators
-
1.
Huygens Institute for History and Culture of the Netherlands
- 2. DHLab - KNAW Humanities Cluster
Description
This repository contains the abstract and presentation of our paper presented at the Digital Humanities in the BeNeLux 2024 (DH Benelux 2024) conference, held 4-7 June at KU Leuven in Leuven Belgium.
In this paper we report on our approach to extracting entities from the REPUBLIC corpus of the resolutions of the States General of the Dutch Republic 1576-1796. We describe 1) the construction of ground truth data for different types of entities, 2) the evaluation of NER taggers based on various types of embeddings for historical Dutch, 3) our findings from curating millions of occurrences of the different entity types, and 4) how the curation gives insights into the characteristics of the corpus.
Files
DH-Benelux-2024-REPUBLIC-NER.pdf
Files
(5.0 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:b0e63ca80439985ccdf3e14768129a94
|
4.5 MB | Preview Download |
|
md5:73670d5fc52cc3d371278536b8b6aa63
|
553.0 kB | Preview Download |
Additional details
Funding
- Dutch Research Council
- REPUBLIC 175.217.024