Multilingual challenges for accessing digitized culture online - Riga Summit 15
Download as PPT, PDF1 like1,439 views
The document discusses the multilingual challenges in accessing digitized cultural heritage online, highlighting the issues of data heterogeneity and the complexity of multilingual enrichment. It emphasizes the diversity of applications and the difficulties in applying language technology to effectively manage and utilize cultural data across Europe. The need for collaboration within the cultural heritage and language technology sectors is stressed, alongside the importance of open data and community sharing.
Multilingual challenges for accessing digitized culture online - Riga Summit 15
- 1. Multilingual challenges for accessing digitized culture online Antoine Isaac Multilingual Digital Single Market Riga Summit, 28 April 2015
- 2. Europe’s platform to access cultural heritage 42M objects and counting
- 3. Built on metadata from a broad network Museums National Aggregators Regional AggregatorsArchives Thematic projects Libraries Musées Lausannois Culture.fr The European Library APEX LinkedHeritage Europeana Fashion 2,300 museums, archives and libraries
- 4. A platform for access and re-use
- 5. Data from all over EU top 16 Items from 36 countries Metadata in 33 languages
- 6. Data from all over EU
- 7. (Re-)users from all over EU Portal in 31 languages Data access from anywhere
- 8. Diversity of domains makes it hard Data is heterogeneous Makes it harder to train tools
- 9. Diversity of applications makes it harder Display Search Data services ….
- 10. Some issues for applying language technology for online culture Typical queries are very short Identification of query language is not easy, even manually Plenty of named entities (persons, places…) Studies by Humboldt University on Europeana and The European Library http://www.clef-initiative.eu/documents/71612/86374/CLEF2010wn-LogCLEF-StillerEt2010.pdf
- 11. Progress and issues – data enrichment
- 12. Problems of multilingual enrichment
- 13. Problems of multilingual enrichment Poisonous India or the Importance of a Semantic and Multilingual Enrichment Strategy Marlies Olensky, Juliane Stiller, Evelyn Dröge, MTSR 2012 http://link.springer.com/chapter/10.1007%2F978-3-642- 35233-1_25
- 14. Exploiting multilingual data from partners
- 15. Problems need pooling resources From cultural heritage sector From language technology industry EU level: Horizon2020 projects, DSIs • MT@EU National level • Cooperation Tilde & Latvian Ministry of Culture
- 16. Being open Open source and open data, as much as possible! Sharing the word about problems and solutions EuropeanaTech Insight first issue on multilingualism
Editor's Notes
- #3: Les Miserables: Victor Hugo’s handwritten manuscripts: http://www.europeana.eu/portal/record/9200103/5372912AF66AB529E188218BC1F747E75EB1A18F.html BnF, public domain Matisse ‘53 in the form of a double helix’ http://www.europeana.eu/portal/record/9200104/F8D60AB9136C8A59B59DF1CFEC278A6CABA8B0C6.htmlThe Wellcome Library (CC-BY-NC-ND) ‘söprűtánc’ – Hungarian traditional dance http://www.europeana.eu/portal/record/08901/E1A7B01BE4AED87FD239672F4F3941F52262D6B2.html Hungarian Academy of Sciences Institute for Musicology, public domain ‘Neurologico reggae’ Music album http://www.europeana.eu/portal/record/08901/ADC241BCBF8470988DBA6EEAFCF13F14D88E5534.html DISMARC – EuropeanaConnect Paid Access ‘Castle of Kavala’ 3D exploration of a Greek castle http://www.europeana.eu/portal/record/2020703/05607B24D15BD516EE2B765F74CDA39C7427F7FB.html Cultural and Educational Technology Institute - Research Centre Athen CARARE CC-BY-NC-ND
- #4: All partners send us descriptions of their assets, which we aggregate in a single service
- #5: Users from everywhere Data from everywhere Tools from everywhere http://europeana.eu/portal/record/2022347/B7C7D15C23C28EFD3FA25147ED3A580757CFBB04.html http://europeana.eu/portal/record/9200103/ark__12148_btv1b6921004c.html
- #6: Germany 15.44% France 10.97% Netherlands 9.67% Sweden 9.44% Spain 9.98% UK 6.98% Norway 6.60% Italy 5.4% Ireland 4.04% Poland 4.02% Europe 3.95% Finland 2.95% Austria 2.05% Belgium 1.61% Hungary 1.26%
- #7: Users from everywhere Data from everywhere Tools from everywhere http://europeana.eu/portal/record/2022347/B7C7D15C23C28EFD3FA25147ED3A580757CFBB04.html http://europeana.eu/portal/record/9200103/ark__12148_btv1b6921004c.html
- #8: Users from everywhere Data from everywhere Tools from everywhere http://europeana.eu/portal/record/2022347/B7C7D15C23C28EFD3FA25147ED3A580757CFBB04.html http://europeana.eu/portal/record/9200103/ark__12148_btv1b6921004c.html
- #9: Tools, UCL Museums, CC-BY-NC-SA Paris, nouvelle machine à paver : [photographie de presse] / [Agence Rol], National Library of France, Public Domain St. Philip holding a book and St. James (the Less?) holding a book, National Library of the Netherlands, Public domain La paloma / O sole mio, Dalane Folkemuseum, CC0 http://europeana.eu/portal/record/2022347/B7C7D15C23C28EFD3FA25147ED3A580757CFBB04.html http://europeana.eu/portal/record/9200103/ark__12148_btv1b6921004c.html http://www.europeana.eu/portal/record/9200122/BibliographicResource_1000056116671.html http://www.europeana.eu/portal/record/2022608/DF_DF_13399.html
- #10: http://www.clef-initiative.eu/documents/71612/86374/CLEF2010wn-LogCLEF-StillerEt2010.pdf
- #11: Average less than 2 terms 39% of queries may belong to several languages 60% of queries are for persons and places