Jump to content

Yandex Translate

From Wikipedia, the free encyclopedia

Yandex Translate

Yandex.Translate homepage in English
Type of site
Neural machine translation
Available in98 languages; see below
Interface: English, Russian, Turkish, Ukrainian
OwnerYandex
URLtranslate.yandex.com (in English)
translate.yandex.ru (in Russian)
ceviri.yandex.com.tr (in Turkish)
CommercialYes
RegistrationOptional
LaunchedMarch 22, 2011; 13 years ago (2011-03-22)[1][2]
Current statusActive

Yandex Translate (Russian: Яндекс Переводчик, romanizedYandeks Perevodchik) is a web service provided by Yandex, intended for the translation of 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 single-word translations 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.

In September 2017, Yandex.Translate switched to a hybrid approach incorporating both statistical machine translation and neural machine translation models.[5]

The translation page first appeared in 2009[citation needed], utilizing PROMT, and was also built into Yandex Browser itself, to assist in translation for websites.

Supported languages

[edit]

Immediately after the launch of the translator in beta mode in the spring of 2010, it was only available in three languages — English, Russian and Ukrainian, with a limit of 10,000 characters.[2]

Yandex.Translate has some languages that are missing from Google Translate, such as Russia's national minority languages.

As of November 2024, translation is available in 99 languages:

  1. Afrikaans
  2. Albanian
  3. Amharic β
  4. Arabic
  5. Armenian
  6. Azerbaijani
  7. Bashkir
  8. Basque
  9. Belarusian
  10. Bengali
  11. Bosnian
  12. Bulgarian
  13. Burmese β
  14. Catalan
  15. Cebuano
  16. Chinese
  17. Chuvash
  18. Croatian
  19. Czech
  20. Danish
  21. Dutch
  22. Elvish (Sindarin) α
  23. Emoji (Not a natural language)
  24. English
  25. Esperanto
  26. Estonian
  27. Finnish
  28. French
  29. Galician
  30. Georgian
  31. German
  32. Greek
  33. Gujarati
  34. Haitian Creole
  35. Hebrew
  36. Hill Mari β
  37. Hindi
  38. Hungarian
  39. Icelandic
  40. Indonesian
  41. Irish
  42. Italian
  43. Japanese
  44. Javanese
  45. Kannada
  46. Kazakh (Cyrillic and Latin)
  47. Khmer
  48. Korean
  49. Kyrgyz β
  50. Lao β
  51. Latin
  52. Latvian
  53. Lithuanian
  54. Luxembourgish
  55. Macedonian
  56. Malagasy
  57. Malay
  58. Malayalam β
  59. Maltese
  60. Māori
  61. Marathi
  62. Meadow Mari β
  63. Mongolian β
  64. Nepali
  65. Norwegian
  66. Ossetian
  67. Papiamento β
  68. Persian
  69. Polish
  70. Portuguese (European and Brazilian)
  71. Punjabi
  72. Romanian
  73. Russian
  74. Scottish Gaelic
  75. Serbian (Cyrillic and Latin)
  76. Sinhala
  77. Slovak
  78. Slovenian
  79. Spanish
  80. Sundanese
  81. Swahili
  82. Swedish
  83. Tagalog
  84. Tajik β
  85. Tamil β
  86. Tatar
  87. Telugu β
  88. Thai
  89. Turkish
  90. Udmurt β
  91. Ukrainian
  92. Urdu
  93. Uzbek (Latin and Cyrillic)
  94. Vietnamese
  95. Welsh
  96. Xhosa β
  97. Yakut β
  98. Yiddish
  99. Zulu

The translation direction is determined automatically. It is possible to translate words, sentences, or web pages if needed. There is also the option to view both the translation and the original at the same time in a two-window view. In addition to machine translation, there is also an accessible and complete English-Russian and Russian-English dictionary.[6] There is an app for devices based on the iOS software,[7] Windows Phone and Android. You can listen to the pronunciation of the translation and the original text using a text to speech converter built in.

Translations of sentences and words can be stored to a "Favorites" section located below the input field.

Limitations

[edit]

Yandex.Translate, like other automatic translation tools, has its limitations. When the online service was first introduced, the head of Yandex.Translate, Alexei Baitin, stated that although machine translation cannot be compared to a literary text, the translations produced by the system can provide a convenient option for understanding the general meaning of the text in a foreign language.[8]

Translation methodology

[edit]

According to Arkady Volozh, founder and CEO of Yandex, the mechanism of Translate is as follows:[9]

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.[10]

Features

[edit]
  • the mobile app for iOS is available for the transliteration of the Arabic, Armenian, Chinese (Pinyin), Georgian, Greek, Hebrew, Japanese, Korean and Persian languages;[11]
  • voice input;
  • photo text translation feature (uses its own OCR (optical character recognition) technology) – in apps for mobile phones;[12]
  • the "Suggest translation" button (user patches to help improve the quality of machine translations);
  • the "Favorites" section, where you can add translations of individual words and sentences;
  • virtual keyboard.

See also

[edit]

References

[edit]
  1. ^ "Яндекс запустил сервис онлайн-перевода". Компания Яндекс (in Russian). Retrieved 5 July 2024.
  2. ^ a b Yandex has got its own interpreter
  3. ^ "Yandex — Technologies — Machine Translation". Yandex. Retrieved 8 June 2016.
  4. ^ ""Yandex" has learned to translate the texts online". vesti.ru. Retrieved 8 June 2016.
  5. ^ "One model is better than two. Yandex.Translate launches a hybrid machine translation system". Yandex Blog. Retrieved 3 October 2019.
  6. ^ Service Yandex.Translation was released out of beta[permanent dead link]
  7. ^ Yandex.Translation — pocket translator for iPhone[permanent dead link]
  8. ^ ""Яндекс" запустил онлайн-переводчик текстов". Lenta.RU (in Russian). Retrieved 5 July 2024.
  9. ^ Sokolov-Mitrich D. V. (2014). Yandex.Book [ru]. Real stories. Moscow: Mann, Ivanov and Ferber [ru]. p. 368. ISBN 978-5-00057-092-0. [ru]&rft.place=Moscow&rft.series=Real stories&rft.pages=368&rft.pub=Mann, Ivanov and Ferber [ru]&rft.date=2014&rft.isbn=978-5-00057-092-0&rft.au=Sokolov-Mitrich D. V.&rfr_id=info:sid/en.wikipedia.org:Yandex Translate" class="Z3988">
  10. ^ ""Yandex" has started to sell services online translation". Archived from the original on 25 August 2014. Retrieved 18 May 2015.
  11. ^ "It's time to travel!". Archived from the original on 10 January 2020. Retrieved 16 July 2016.
  12. ^ "Translate photo". Archived from the original on 13 September 2015. Retrieved 16 July 2016.
[edit]