The main source on which they usually train the translation systems is called parallel text corpus | The Google Translate app for iOS has been updated with Hebrew and Arabic voice input, Slovak and Thai text to speech, Esperanto translation, and Tap to Copy |
---|---|
Note that these are pronounced slightly differently | What all of these translations had in common was the use of words taken from political and religious contexts: Islamic organizations, the US Department of Defense, State Department, Islamic Republic of Iran, United Arab Emirates, and the Koran appeared repeatedly, |
But nonetheless, someone who speaks French definitely cannot understand Spanish, nor vice versa.
11On this basis, it assigns the text to a specific set of concepts, from which it derives the likeliest translation for the words it does not recognize | The errors in Arabic and Farsi are, of course, not the first time that Google has made translation mistakes |
---|---|
Also, its grammar is about identical in complexity to nearly all other spoken Arabic dialects | Google added the options of translation between English and Farsi before the they had planned to do it because of the turbulent political situation then |
The results were similar: instead of getting an error message that the text in Farsi was meaningless, Google Translate proposed completely imaginary translations.
29