Some time ago, a neural network based on artificial intelligence was connected to the Google Translate system to speed up the translation processes into several of the most common languages. But after a while the machine translator learned to recognize and those languages that were not inherent in it initially. This became possible due to the fact that the artificial mind independently created an "intermediate" language, which is used to translate from one adverb to another.
Google Translate, unlike other online translators, translates the entire sentence without breaking it into separate words. Of course, the quality is still far from ideal, but it is constantly improving. Because of the grammatical difference between languages for translating phrases and sentences, it is necessary to use different language modules that are different for each language. The neural network, having systematized the information of these modules, has created its own "medium" version, which is used for translation.
Thus, at first the system translates the language into this "average" fictional, and already with it is capable of making a translation to any other. For example, initially the system was taught the translation between English and Japanese, as well as English and Korean. Then the system itself learned to do the translation from Japanese into Korean, bypassing the English language. Many specialists see great potential in this system. For example, Kyunghong Cho, a semantics specialist from New York University, says:
"The method of translation implemented by Google's specialists is more complicated than any other method. But nevertheless, this direction is developing very rapidly, and in the near future such systems will become the main means of automatic translation. I have no doubt that we will create and train an automatic translation system based on a single neural network, which will master more than a hundred different languages at the same time. "
The article is based on materials .
Comments
Post a Comment