Nasza strona zapisuje niewielkie pliki tekstowe, nazywane ciasteczkami (ang. cookies) na Twoim urządzeniu w celu lepszego dostosowania treści oraz dla celów statystycznych. Możesz wyłączyć możliwość ich zapisu, zmieniając ustawienia Twojej przeglądarki. Korzystanie z naszej strony bez zmiany ustawień oznacza zgodę na przechowywanie cookies w Twoim urządzeniu.
In our work we see that the quality of translation has improved due to the creation of models of translation from Turkish to English and from English to Turkic languages. Turkic-speaking languages are structurally similar. Therefore, studying one of the Turkic languages, you can assemble a corpus for other languages and apply it to the same model. This is done using the OpenNMT model (open neural machine translation). The article shows the morphological, lexical, semantic increase of BlEU (translation index) words and sentences of Turkic languages using OpenNMT. To increase the value of BLEU it is necessary to increase the base in the case. In addition, the work provides a detailed description of the construction of OpenNMT models. Experiments with the Kazakh language, one of the Turkic languages, were conducted and the results were obtained. Words in the Kazakh language taken from the news. The scientific work includes a review of the work of scientists who studied neural machine translation. It is shown that the results of this work outperform the work of other researchers. Having created the neural model of OpenNMT, you will see that the result of the translation is not the same as the online translation from Google, Yandex. OpenNMT also takes less time to read data and saves memory. The results of the experimental study show that the Kazakh-English and English-Kazakh language pairs gave good results in translation.