Перегляд за Автор "Orobinska, Olena"
Зараз показуємо 1 - 3 з 3
Результатів на сторінці
Налаштування сортування
Документ Construction and Analysis of Berber Text Corpus(2020) Zayd, Khayi; Orobinska, OlenaThis work is devoted to constructing a tool to analyze the different aspects of Berber languages. It is based on grammatical parameters of these languages. The text collection containing more than 500 texts that cover long historic period was collected. The corpus is free available and it will useful for further investigations on Tamazigh language. It was transformed into xml-format standardization goal. The corpus counts more than 200 000 of words. Based on the linguistic rules and statistic methods, original user interface and software prototype were developed by combining the technologies of web design and object programming in Python.Документ Methods and models of automatic ontology construction for specialized domains (case of the Radiation Security)(2017) Orobinska, Olena; Chauchat, Jean-Hugues; Sharonova, Natalia ValeriyevnaWe propose a hybrid, semi-automatic approach that uses the intersection of semantic classes of nouns and verbs built on the domain lexicon and builds kernel ontology from a list of initial concepts and then completes this kernel ontology by new entities detected in a large corpus of texts of international standards of Radiological Safety. The results confirm the important role of initial linguistic modeling and show that the external lexical resources available online can contribute effectively to the resolution of the problem of lexical disambiguation.Документ Semantic Similarity Detection in a Single Text(2020) Polityuk, Anna; Orobinska, OlenaTo solve many of the problems of automatic natural language processing, it is often necessary to have a dictionary of synonymous terms. To simplify its using is objective of our experiment. We propose the method that realize the lexical approach and provide the detecting all synonyms in a single text and visualize the results directly in the text. The results depend on the completeness of the lexical source. But it is a bottleneck problem of most of thesaurus.