Jump to content

Google Translate

From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by 77.86.76.47 (talk) at 02:39, 23 July 2010 (Language options). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

Google Translate
File:Google Translate logo.png
File:Google Translate.PNG
Type of site
translation
OwnerGoogle
Created byGoogle
URLhttp://translate.google.com/
RegistrationNo

Google Translate is a free machine translation service provided by Google Inc. to translate a section of text, or a webpage, into another language.

The statistically based translation service was introduced in 2007, prior to that Google used a SYSTRAN] based translator[1] which is used by other translation services such as Babel Fish, AOL, and Yahoo.

Features and limitations

The service limits the number of paragraphs, or range of technical terms, that will be translated. It is also possible to enter searches in a source language that are first translated to a destination language allowing you to browse and interpret results from the selected destination language in the source language. [2] For some languages, users are asked for alternate translations such as for technical terms, to be included for future updates to the translation process. Text in a foreign language can be typed, and if "Detect Language" is selected, it will not only detect the language, but it will translate into English by default.

Google Translate, like other automatic translation tools, has its limitations. While it can help the reader to understand the general content of a foreign language text, it does not always deliver accurate translations. Some languages produce better results than others, as of 2010 french to english translation is very good,[3] however rules based translators perform better as the length of text to be translate becomes shorter; this effect is particularly prescient for chinese to english translations.[3]

Languages written in Greek alphabet, Devanagari, Cyrillic script, or the Arabic script and its variants can be transliterated automatically from phonetic equivalents written in the Latin alphabet.

Browser integration

A number of Firefox extensions exist for Google services, and likewise for Google Translate, which allow right-click command access to the translation service. [4]

A extension for google chrome browser also exists[5]; in Febuary 2010 Google translate was integrated into the standard Google Chrome browser.[6][7]

Language options

(by chronological order of introduction)

  • 1st stage
     
  • French to English
  • German to English
  • Spanish to English
  • 2nd stage
  • Portuguese to English
  • Dutch to English
  • 3rd stage
  • Italian to English
  • 4th stage
     
  • Chinese (Simplified) to English
  • Japanese to English
  • Korean to English
  • 5th stage (launched December 2006)
  • Russian to English
  • 6th stage (launched April 2007)
  • Arabic to English
  • 7th stage (launched February 2007)
  • English to Chinese (Traditional)
  • Chinese (Simplified to Traditional)
     
  • Chinese (Traditional) to English
  • Chinese (Traditional to Simplified)
  • 8th stage (launched October 2007)
    • all 25 language pairs use Google's machine translation system
  • 9th stage
  • Hindi to English
  • 10th stage (as of this stage, translation can be done between any two languages, going through English, if needed) (launched May 2008)
           
  • 11th stage (launched September 25, 2008)
                 
  • 12th stage (launched January 30, 2009)
               
  • 13th stage (launched June 19, 2009)
  • 14th stage (launched August 24, 2009)
                       
  • 15th stage (launched November 19, 2009)
    • The Beta stage is finished. Users can now choose to have the romanization written for Chinese, Japanese, Korean, Russian, Ukrainian, Belarusian, Bulgarian, Greek, Hindi and Thai. For translations from Arabic, Persian and Hindi, the user can enter a Latin transliteration of the text and the text will be translated to the native script for these languages as the user is writing. The text can now be read by a text-to-speech program in English, Italian, French and German
  • 16th stage (launched January 30, 2010)
  • 17th stage (launched April 2010)
    • Speech program launched in Hindi and Spanish
  • 18th stage (launched May 5, 2010)
    • Speech program launched in Afrikaans, Albanian, Catalan, Chinese (Mandarin), Croatian, Czech, Danish, Dutch, Finnish, Greek, Hungarian, Icelandic, Indonesian, Latvian, Macedonian, Norwegian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Swahili, Swedish, Turkish, Vietnamese and Welsh (based in eSpeak)[8].
  • 19th stage (launched May 13, 2010[9])
               
  • 20th stage (launched June 2010)
  • Provides romanization for Arabic.

Translation methodology

It does not apply grammatical rules, since its algorithms are based on statistical analysis rather than traditional rule-based analysis.[10]

Google translate is based on an approach called statistical machine translation, and more specifically, on research by Franz-Josef Och who won the DARPA contest for speed machine translation in 2003. Och is now the head of Google's machine translation department.

According to Och,[11] a solid base for developing a usable statistical machine translation system for a new pair of languages from scratch, would consist in having a bilingual text corpus (or parallel collection) of more than a million words and two monolingual corpora of each more than a billion words. Statistical models from this data are then used to translate between those languages.

To acquire this huge amount of linguistic data, Google used United Nations documents.[12] The same document is normally available in all six official UN languages (Arabic, Chinese, English, French, Russian, Spanish), so Google now has a 6-language corpus of 20 billion words' worth of human translations.[citation needed]

The availability of Arabic and Chinese as official UN languages is probably one of the reasons why Google Translate initially focused on the development of translation between English and those languages, and not, for example, Japanese and German, which are not official languages at the UN.[citation needed]

Google representatives have been very active at domestic conferences in Japan in the field asking researchers to provide them with bilingual corpora.[13][citation needed]

Translation mistakes and oddities

Because[citation needed] Google Translate uses statistical matching to translate rather than a dictionary/grammar rules approach translated text can often include apparently nonsensical and obvious errors;[14] often swapping common terms for similar but non equivalent common terms in the other language,[15] as well as inverting sentence meaning.[16].

See also

References

  1. ^ Google Translate Drops Systran For Home Brewed Translation 23/12/2007 , Barry Schwartz , searchengineland.com
  2. ^ "Google Translate". Google. Retrieved 2009-01-24.
  3. ^ a b Comparison of online machine translation tools 6/2010 , Ethan Shen , www.tcworld.info
  4. ^ "Search Add-ons :: Add-ons for Firefox". Mozilla. Retrieved 2009-08-07.
  5. ^ Google Translate by chrome.translate.extension chrome.google.com
  6. ^ Google Translate Integrated In Google Chrome 5
  7. ^ Google Chrome 5 features an integrated Google Translate service 15/2/2010 , stuff.techwhack.com
  8. ^ http://googleblog.blogspot.com/2010/05/giving-voice-to-more-languages-on.html
  9. ^ http://googletranslate.blogspot.com/2010/05/five-more-languages-on.html
  10. ^ Franz-Josef Och confirmed this during his keynote speech at the MT Summit 2005, stating that "We do not need rules any more."
  11. ^ Keynote speech at the Machine Translation Summit 2005
  12. ^ Google seeks world of instant translations (Reuters)
  13. ^ Google was an official sponsor of the annual Computational Linguistics in Japan Conference ("Gengoshorigakkai") in 2007. Google also sent a delegate from its headquarters to the meeting of the members of the Computational Linguistic Society of Japan in March 2005, promising funding to researchers who would be willing to share text data.
  14. ^ Google Translate Tangles With Computer Learning Lee Gomes , Forbes Magazine , 9/8/2010
  15. ^ Google Translates Ivan the Terrible as “Abraham Lincoln” google.blognewschannel.com
  16. ^ Google Lost in Translation 28/01/2010 , Alyona Topolyanskaya , www,mn.ru