Corpus of Alisher Navoi - Automatic Semantic Descriptor System of Historical Words
Abstract
The article was created in order to study the scientific and creative heritage of Alisher Navoi, a phenomenon of the Turkish peoples, to read and understand his works, and to present the language of the XV century in modern Uzbek. The composition of Alisher Navoi's authorship corpus, semantic tags and automatic semantic description of archaic and obsolete words in the corpus are discussed. As a result of the linguistic changes in our language from the point of view of the period, it is natural that the thoughts, ideas and goals expressed in Navoi's works are incomprehensible to today's readers. It is known that in the poet's ghazals there are many stanzas with the names of historical, literary, mythical, geographical and ethnic places. This phenomenon gives rise to the poetic art of talmeh in literature and scientifically, the reader gets information about historical and famous people and geographical place names in the process of determining the meaning of the words. This article also contains information about Alisher Navoi's authorship corpus being a system for automatic semantic description of historical words.