Discriminating The Registers And Styles In The Modern Greek Language

This article investigates (a) whether register discrimination can successfully exploit linguistic information reflecting the evolution of a language (such as the diglossia phenomenon of the Modern Greek language) and (b) what kind of linguistic information and which statistical techniques may be employed to distinguish among individual styles within one register. Using clustering techniques and features reflecting the diglossia phenomenon, we have successfully discriminated registers in Modem Greek. However, diglossia information has not been shown sufficient to distinguish among individual styles within one register. Instead, a large number of linguistic features need to be studied with methods such as discriminant analysis in order to obtain a high degree of discrimination accuracy.