Conference paper Open Access

Linking Named Entities in Dutch Historical Newspapers

van Veen, Theo; Lonij, Juliette; Faber, Willem Jan

We improved access to the collection of Dutch historical newspapers of the Koninklijke Bibliotheek by linking named entities in the newspaper articles to corresponding Wikidata descriptions by means of machine learning techniques and crowdsourcing. Indexing the Wikidata identifiers for named entities together with the newspaper articles opens up new possibilities for retrieving articles that mention these resources and searching the newspaper collection using semantic relations from Wikidata. In this paper we describe our steps so far in setting up this combination of entity linking, machine learning and crowdsourcing in our research environment as well as our planned activities aimed at improving the quality of the links and extending the semantic search capabilities.

The final publication is available at Springer via https://doi.org/10.1007/978-3-319-49157-8_18.
Files (143.3 kB)
Name Size
LinkingNamedEntitiesInDutchHistoricalNewspapers-VanVeenLonijFaber-49-MTSR2016.pdf
md5:0e2360fa17a4dff81a075155220e4506
143.3 kB Download
101
39
views
downloads
All versions This version
Views 101101
Downloads 3939
Data volume 5.6 MB5.6 MB
Unique views 9393
Unique downloads 3636

Share

Cite as