europeananews

BIO-tagged news articles in different languages extracted from <a href="https://github.com/EuropeanaNewspapers/ner-corpora">https://github.com/EuropeanaNewspapers/ner-corpora</a> 
using <code>europeana_read</code><ul>
<li>Dutch from the Koninklijke Bibliotheek</li>
<li>Austrian from the National Library of Austria</li>
<li>German from the Dr. Friedrich Teßmann Library</li>
<li>French from the National Library of France, in cooperation with LIP6-ACASA</li>
</ul>

Wraps the 'nametag' library <https://github.com/ufal/nametag>, allowing users to find and extract entities (names, persons, locations, addresses, ...) in raw text and build your own entity recognition models.
Based on a maximum entropy Markov model which is described in Strakova J., Straka M. and Hajic J. (2013) <https://ufal.mff.cuni.cz/~straka/papers/2013-tsd_ner.pdf>.

Jan Wijffels

nametagger

Named Entity Recognition in Texts using 'NameTag'

BNOSAC 

Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics, Charles University in Prague, Czech Republic 

Milan Straka 

Jana Straková 

europeananews function

BIO-tagged news articles in different languages extracted from <a href='https://github.com/EuropeanaNewspapers/ner-corpora'>https://github.com/EuropeanaNewspapers/ner-corpora</a> 
using <code>europeana_read</code><ul>
<li>Dutch from the Koninklijke Bibliotheek</li>
<li>Austrian from the National Library of Austria</li>
<li>German from the Dr. Friedrich Teßmann Library</li>
<li>French from the National Library of France, in cooperation with LIP6-ACASA</li>
</ul>

europeananews: Tagged news paper articles from Europeana

Description

Arguments

References

Examples