%0 Conference Proceedings
%4 sid.inpe.br/mtc-m16c/2015/12.10.17.45
%2 sid.inpe.br/mtc-m16c/2015/12.10.17.45.51
%@issn 2179-4820
%T Mining influential terms for toponym recognition and resolution
%D 2015
%A Jerônimo, Caio Libânio Melo,
%A Campelo, Cláudio E. C.,
%A Baptista, Cláudio de Souza,
%@affiliation Universidade Federal de Campina Grande (UFCG)
%@affiliation Universidade Federal de Campina Grande (UFCG)
%@affiliation Universidade Federal de Campina Grande (UFCG)
%E Fileto, Renato,
%E Korting, Thales Sehn,
%B Simpósio Brasileiro de Geoinformática, 16 (GEOINFO)
%C Campos do Jordão
%8 27 nov. a 02 dez. 2015
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%P 143-154
%S Anais
%X The detection of toponyms present in text has appeared as a useful resource for many different applications, such as for social network analysers and for geographic search engines. The variety of ambiguities present in the geoparsing process represents one of the main challenges related to the process of detecting toponyms, bringing the need for treating this problem with careful attention. One important technique to detect toponyms is based on the presence of influential terms, which are terms that could indicate the existence of geographical references in the text. This paper presents an approach to automatically identifying relevant influential terms for a given language, as well as a set of attributes relating these terms with toponyms. The technique presented here was validated with an existing geoparser, using a training set based on online news. The results indicate the technique is effective in identifying influential terms, and has shown that the geoparsers capabilities of detecting toponyms have improved by using the generated list of influential terms.
%@language en
%3 proceedings2015_p14.pdf