Leksikograafilise tarkvara Sketch Engine eesti keele moodul

Jelena Kallas, Maria Tuulik, and Madis Jürviste: Estonian language module of lexicographic software Sketch Engine. The Sketch Engine is a software aiming to analyse corpus data. Its main functions being the compilation and varied analysis of concordances, creating frequency lists, automatic compilation of word sketches and distributive thesauruses. In the autumn of 2010 the Institute of the Estonian Language started to develop, in collaboration with Lexical Computing Ltd., the Estonian language module for the Sketch Engine software. The Estonian Sketch Engine consists of a 250-million word Estonian Reference Corpus. The article gives an overview of Estonian Word Sketch grammar compilation principles. The authors demonstrate word sketches for nouns, verbs and adjectives. Also, an insight is given into the possibilities of further development of the Estonian language module. The corpus-based approach being one of the most widespread tendencies in modern linguistics, it is of utmost importance for Estonian language research to promote the usage of programs such as the Sketch Engine.