Scientific publications

The Open corpus of Veps and Karelian languages (VepKar) is useful both for linguists and dialectologists, since dialect texts are given with a detailed description: informant's name, year and place of his birth, place of recording, dialect, etc. The article discusses the features of the smallest Ludian subcorpus. The architecture of the developed corpus manager dictorpus (used in the VepKar) is presented in the article. Semantic and morphological tags links texts with VepKar dictionary entries. Semantic categorization of the meanings of lemmas is planned to be based on categories from the comparative onomasiological dictionary. As part of future work, the morphological analyzer will be developed on the basis of finite state machines.