Метод веб-извлечения парадигм русских глаголов из электронных словарей и баз данных. Матричная организация лакун, их кодификация и классификация (на материале глаголов звучания). Рабочие тезисы. Февраль
At present linguists have access to digital collections of dictionaries and language samples known as “corpora”. Data mining using these sources allows to statistically verify the words’ (wordforms’) codification, determine their frequency of usage with respect to grammatical and colloquial contexts. Data collected by using the web scraping methodology in this research may be used on their own or in combination with data collected from other big data sources. This project is especially significant for the “rich morphology” languages. Different strategies may be applied for gathering, visualizing, or analyzing data from various online Russian dictionaries, corpora, or from other big data sources using digital technologies (e.g., from web portals, to computer-assisted text collections, etc.).
Dr. Irina V. Ivliyeva, ivliyeva@mst.edu
Professor of Russian, Arts, Languages, and Philosophy Department
Missouri University of Science and Technology
Perry B. Koob, koobp@mst.edu
Database Administrator/System Administrator
Academic Technology Support Team
Missouri S&T Information Technology
Available at: http://works.bepress.com/irina-ivliyeva/52/