The research activities in Språkbanken focus on creating, refining and making available linguistic resources, with the aim of making these resources useful for research and higher education. We build and develop research infrastructure - e-science - for a number of disciplines, primarily language technology and linguistics, but also humanities and social science disciplines, as well as medicine.
The linguistic resources are mainly corpora and lexical resources, together with language technology tools for refinement and use of the corpora and lexicons. Refinement includes, e.g., the automatic addition to corpus texts of linguistic information, i.e. parts of speech, lemmas, syntactic roles, semantic categories, etc. This facilitates more sophisticated quantitative and qualitative linguistic research than would be possible using only the text itself. In particular, the addition of various types of semantic information is key to the use of text as primary research data in other disciplines than linguistics.
Information about some of our current research projects is available via the links in the left-hand column. More information about Språkbanken's resources can be found under Resources.