A Computational Approach to Recognizing Poetry Genres in Uzbek Texts

In the research paper, the authors propose an algorithm for detecting poetic elements, words, and phrases in Uzbek texts. In addition, during analyzing the algorithm classifies poetic tokens in of the of 2 poetic genres (comedy, drama). In particular, the researchers trained a language model of artificial intelligence with an architectural combination of a convolutional neural network and long short-term memory. A custom language corpus was used as training data. This corpus was formed from more than 3,600 literary sentences, which in turn were selected from U zbek poetic works of the 20th century. Words and phrases in the corpus sentences were tagged according to the BIO-scheme, which the authors also talk about in the corresponding section of the article. Moreover, the authors also included information about the morphology of the U zbek language so that the context of this study was more understandable to all readers. In addition, the authors also conducted a comparative analysis of existing alternative works, where they provide the features of each similar work.