Automated extraction of lexical meanings from Polish corpora: potentialities and limitations

Abstract

Automated extraction of lexical meanings from Polish corpora: potentialities and limitations

Large corpora are often consulted by linguists as a knowledge source with respect to lexicon, morphology or syntax. However, there are also several methods of automated extraction of semantic properties of language units from corpora. In the paper we focus on emerging potentialities of these methods, as well as on their identified limitations. Evidence that can be collected from corpora is confronted with the existing models of formalised description of lexical meanings. Two basic paradigms of lexical semantics extraction are briefly described. Their properties are analysed on the basis of several experiments performed on Polish corpora. Several potential applications of the methods, including a system supporting expansion of a Polish wordnet, are discussed. Finally, perspectives on the potential further development are discussed.