Yandex.Translate

Yandex.Translate
Type of site
Statistical machine translation
Available in 90 languages, see features
Interface: English, Russian, Turkish, Ukrainian
Owner Yandex
Website translate.yandex.com (in English)
translate.yandex.ru (in Russian)
ceviri.yandex.com.tr (in Turkish)
translate.yandex.ua (in Ukrainian)
Commercial Yes
Registration Optional
Launched March 22, 2011 (2011-03-22)[1][2]
Current status Active

Yandex.Translate (previously Yandex.Translation) is a web service provided by Yandex, intended for the translation of text or web pages into another language.

The service uses a self-learning statistical machine translation,[3] developed by Yandex.[4] The system constructs the dictionary of correspondences based on the analysis of millions of translated texts. In order to translate the text, the computer first compares it to a database of words. The computer then compares the text to the base language models, trying to determine the meaning of an expression in the context of the text.

The translation function obtained in the search results pages (on the button "Translate") appeared in 2009 and was carried out on the basis of PROMT.

Built in the Russian Wikipedia (translation from English into Russian).[5][6]

In addition, the translator is built into the Yandex.Browser and automatically offers to translate text from supported foreign languages.

Supported languages

Immediately after the launch of the translator in beta mode in the spring of 2011, it was only available in three languages — English, Russian and Ukrainian, with a limit of 10,000 characters.[2]

As of December 2016, translation is available in 90 languages:

The translation direction is determined automatically. There is the possible translation of single words, whole texts and individual web pages. When you manually enter text, the system will prompt the pop-up window. There is the possibility of a two-window view of the translation and the original web pages. In addition to machine translation, there is also an accessible and complete English-Russian and Russian-English dictionary.[7] There is an app for devices based on the iOS software,[8] Windows Phone and Android. You can listen to the pronunciation of the translation and the original text (synthesised female voice).

Translations of sentences and words can be added to "Favorites" — the relevant section is below the input field.[9]

Limitations

Yandex.Translate, like other automatic translation tools, has its limitations. This tool is intended to help the reader understand the general meaning of the text in a foreign language, but it does not provide accurate translations. According to the head of the service, Alexei Baitin, machine translation cannot by compared to a literary text.[10] We are constantly working on the quality of the translations, translations to other languages are being developed.

Translation methodology

According to Arkady Volozh, the mechanism of Translate is as follows:[11]

Previously, machine translation was based on "the meaning of the text" model: take any language, translate the words in the universal language of the senses, and then translate these meanings in the words of another language - and obtain the translated text. This model prevailed in the 1970s-1980s and automated in the 1990s. All translations of the 1990s built on this ideology. In the 2000s, there was a search, and it became clear: to translate the text, does not necessarily understand the meaning. Humanity has translated so much already that the probability of finding two similar network in the text in different languages is quite large. How to determine that it is the same text? Very simple. They contain many of the same words. If the document of 1,000 words dictionary 800 are a pair, then most likely, it is a translation from one language to another. And then it is already possible to break the text into paragraphs, to offer and something to do with this work. That is, the machine translations are not words, but finished pieces, the machine is capable of doing. In fact, if you think about it, this method of translation even more consistent with the way a person learns the language as a child in real life. After all, we hardly think in terms of "meaning-text", when we say, for example: "Take a pear".

In addition to the free version for users, there is a commercial API online translator (free up to 10 million characters, then paid), designed primarily for the localization of sites of Internet shops and travel companies.[12]

Features

See also

References

External links

This article is issued from Wikipedia - version of the 11/16/2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.