@inproceedings{395cac7343f24ceca854e7c5f4dd8592,
title = "Opening digitized newspapers corpora: Europeana’s full-text data interoperability case",
abstract = "Cultural heritage institutions hold collections of printed newspapers that are valuable resources for the study of history, linguistics and other Digital Humanities scientific domains. Effective retrieval of newspapers content based on metadata only is a task nearly impossible, making the retrieval based on (digitized) full-text particularly relevant. Europeana, Europe’s Digital Library, is in the position to provide access to large newspapers collections with full-text resources. Full-text corpora are also relevant for Europeana’s objective of promoting the usage of cultural heritage resources for use within research infrastructures. We have derived requirements for aggregating and publishing Europeana’s newspapers full-text corpus in an interoperable way, based on investigations into the specific characteristics of cultural data, the needs of two research infrastructures (CLARIN and EUDAT) and the practices being promoted in the International Image Interoperability Framework (IIIF) community. We have then defined a “full-text profile” for the Europeana Data Model, which is being applied to Europeana’s newspaper corpus.",
keywords = "Cultural heritage, Data aggregation, Full-text, Interoperability, Metadata, Research infrastructures",
author = "Nuno Freire and Antoine Isaac and Twan Goosen and Daan Broeder and Hugo Manguinhas and Valentine Charles",
year = "2019",
month = "5",
day = "1",
doi = "10.4230/OASIcs.LDK.2019.22",
language = "English",
series = "OpenAccess Series in Informatics",
publisher = "Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing",
pages = "1--14",
editor = "Maria Eskevich and {de Melo}, Gerard and Christian Fath and McCrae, {John P.} and Paul Buitelaar and Christian Chiarcos and Bettina Klimek and Milan Dojchinovski",
booktitle = "2nd Conference on Language, Data and Knowledge, LDK 2019",
}