Exploratory Information Extraction from a Historical Dictionary

We describe a preliminary project of extracting information from an extant dictionary of historical biographies, the "Dicionário Histórico-Biográfico Brasileiro" (the Brazilian Historical and Biographical Dictionary, shortened as DHBB), a longstanding project at the \´Centro de Pesquisa e Documentação de História Contemporânea do Brasil\´ (CPDOC) of the Fundação Getulio Vargas (FGV). For information extraction, we rely on Natural Language Processing tools such as FreeLing as well as our resources NomLex-PT, a lexicon of nominalizations, and OpenWN-PT, a Portuguese version of Princeton\´s WordNet database. While our project currently highlights the potential of information extraction in a fun exploratory manner, we also discuss the engaging of historians interested in the affordances of digital tools.