English-Mongolian, Mongolian-English Neural Machine Translation

Abstract

The latest neural machine translation not only performs better than systems that consider simple words and sentence structures, but also finds a delicate connection between source and target words. Neural machine translation provides a simple modeling mechanism that is easy to use in practice and science. Thus, it does not require concepts such as word ranking, a key component of the system that takes into account the structure of words and sentences. While this simplicity may be seen as an advantage, on the other hand, the lack of careful spelling is to lose control of the translation. Systems that take into account the structure of words and sentences create translations consisting of word sequences in the curriculum data. On the other hand, the neural machine translation is more flexible in terms of translations that don't exactly match the training data. This provides more opportunities for such models, but exempts translation from pre-determined restrictions. Failure to connect specific words can make it difficult to connect the target words you create to the original word. The widespread use of neural networks in the translation system has the advantage of allowing users to translate certain terms and translate uneducated data to a certain extent. In some cases, however, the structure of a sentence is often distorted. The paper is intended to address issues such as the control of neural machine translation, more accurate translation of unidentified data, the accuracy of sentence structure and grammar boundaries.