A comparison of methods for the automatic identification of locations in wikipedia

Davide Buscaldi, Paolo Rosso
2007 Proceedings of the 4th ACM workshop on Geographical information retrieval - GIR '07  
In this paper we compare two methods for the automatic identification of geographical articles in encyclopedic resources such as Wikipedia. The methods are a WordNet-based method that uses a set of keywords related to geographical places, and a multinomial Naïve Bayes classificator, trained over a randomly selected subset of the English Wikipedia. This task may be included into the broader task of Named Entity classification, a well-known problem in the field of Natural Language Processing. The
more » ... experiments were carried out considering both the full text of the articles and only the definition of the entity being described in the article. The obtained results show that the information contained in the page templates and the category labels is more useful than the text of the articles.
doi:10.1145/1316948.1316971 dblp:conf/gir/BuscaldiR07 fatcat:l4o7zawv5fheljvkffwo264yu4