Translations

In rude countries, purchasing materials for living is very difficult and the mind will never go beyond consideration of this problem.

For those familiar with French, this is a terrible translation. It often happens that the meaning of the word is incorrect (convert "humble" to "humiliation" and change it to "humiliation" rather than an accurate "humble" meaning or "journey"). Translate to "travel" or "travel", select the wrong subject of the verb and make a grammatical mistake (eg "pour qui tu es devenu" is not all five, only one child It points.). It is a state. This is an attempt to translate the French translation of Facebook to English and to inform you what their machine is saying:

There are two ways to translate content. One way is to use translation services such as machine translation and Google translation. To do this, you simply send it to your text and get a translated version of it. This sounds perfect, but if you've used Google Translate, you probably know that the translation is far from perfect. I can not handle sentences well and there is no context for different words (from right to right). Despite the high-quality translation, there are several good and famous applications that use this method. For example, Ali Express is one of them. Machine translation is used to support all languages. Please look at the "qualitative" example below.

Machine translation (MT) automatically translates text from one natural language (source language) to another language (target language) using machine capabilities. The idea of ​​using a machine for translation was first proposed by Warren Weaver in 1949. Machine translation has been done for a long time (from the 1950's to the 1980's) by studying the language information of the source language and the translation language and generating a translation based on the dictionary. And the grammar is called Rule Based Machine Translation (RBMT). Along with the development of statistics, statistical models became applied to machine translation, and translations were generated based on analysis of bilingual text corpus. This approach, known as Statistical Machine Translation (SMT), achieved superior performance than RBMT and swept the early 1980s and early 2000s. Their research has laid the foundation for the future application of neural networks in machine translation.