Charles Explorer logo
🇬🇧

Where do I Belong in Six Centuries of Literature?

Publication

Abstract

Enhancing the availability of corpora and processing tools for language research is a central endeavour of the CLARIN research infrastructure. In this chapter we report on how PORTULAN CLARIN, with the support of the national institute for the promotion of the Portuguese Language, Camões I.P., has con-tributed to this effort through the development of BDCamões. This is a collec-tion of Portuguese literary documents suited to a variety of research purposes in the science and technology of the Portuguese language. This collection comple-ments existing corpora by virtue of being composed of complete documents, from various genres and prominent authors, covering a wide time span, and offers an important potential for language science and for the development of language technology tools. This chapter also presents and discusses an exemplar case of the exploration of that potential where an automatic authorial style attribution system was developed by resorting to BDCamões.