Thesis Details
Derivační morfologie češtiny na základě rozsáhlých korpusových dat
Subject of this thesis is study of word formation in the Czech language. The main aim is to create a module acquiring derivations from data of the electronic Dictionary of the Czech Language. This problematics has been solved by constructing three-level processing based on dictionary data. The first level is to obtain derivations from lemma definitions, the second step is making groups of basic forms according to their similarities, and the third stage is the evaluation of derivation pairs by number tag of derivation class to which they belong. I have managed to get more than 4 500 new words and evaluate over 20 000 derivative couples. The module has become a full-fledged part of the Morphological Analyzer of the Knowledge Technology Research Group, working at the Faculty of Information Technology of the Brno University of Technology.
czech language, morphology, morpheme, word-formation, derivation, suffixation, internal linguistics, external linguistics, psycholinguistics, sociolinguistics, Dictionary of Czech, derivative classes, nesting
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Hliněná Dana, doc. RNDr., Ph.D. (DMAT FEEC BUT), člen
Matoušek Petr, doc. Ing., Ph.D., M.A. (DIFS FIT BUT), člen
Zachariášová Marcela, Ing., Ph.D. (DCSY FIT BUT), člen
@bachelorsthesis{FITBT20114, author = "Marie Faltusov\'{a}", type = "Bachelor's thesis", title = "Deriva\v{c}n\'{i} morfologie \v{c}e\v{s}tiny na z\'{a}klad\v{e} rozs\'{a}hl\'{y}ch korpusov\'{y}ch dat", school = "Brno University of Technology, Faculty of Information Technology", year = 2017, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/20114/" }