This article needs to be updated. (May 2018)
Google Translate is a free multilingual machine translation service developed by Google, to translate text. It offers a website interface, mobile apps for Android and iOS, and an API that helps developers build browser extensions and software applications. Google Translate supports over 100 languages at various levels and as of May 2017, serves over 500 million people daily.
Launched in April 2006 as a statistical machine translation service, it used United Nations and European Parliament transcripts to gather linguistic data. Rather than translating languages directly, it first translates text to English and then to the target language. During a translation, it looks for patterns in millions of documents to help decide on the best translation. Its accuracy has been criticized and ridiculed on several occasions. In November 2016, Google announced that Google Translate would switch to a neural machine translation engine - Google Neural Machine Translation (GNMT) - which translates "whole sentences at a time, rather than just piece by piece. It uses this broader context to help it figure out the most relevant translation, which it then rearranges and adjusts to be more like a human speaking with proper grammar". Originally only enabled for a few languages in 2016, GNMT is gradually being used for more languages.
Google Translate can translate multiple forms of text and media, including text, speech, images, sites, or real-time video, from one language to another. It supports over 100 languages at various levels and as of May 2017, serves over 500 million people daily. For some languages, Google Translate can pronounce translated text, highlight corresponding words and phrases in the source and target text, and act as a simple dictionary for single-word input. If "Detect language" is selected, text in an unknown language can be automatically identified. If a user enters a URL in the source text, Google Translate will produce a hyperlink to a machine translation of the website. Users can save translations in a "phrasebook" for later use. For some languages, text can be entered via an on-screen keyboard, through handwriting recognition, or speech recognition.
Google Translate is available in some web browsers as an optional downloadable extension that can run the translation engine. In February 2010, Google Translate was integrated into the Google Chrome browser by default, for optional automatic webpage translation.
The Google Translate app for Android and iOS supports more than 100 languages and can translate 37 languages via photo, 32 via voice in "conversation mode", and 27 via real-time video in "augmented reality mode".
The Android app was released in January 2010, and for iOS on February 8, 2011.
A January 2011 Android version experimented with a "Conversation Mode" that allowed users to communicate fluidly with a nearby person in another language. Originally limited to English and Spanish, the feature received support for 12 new languages, still in testing, the following October.
In January 2015, the apps gained the ability to translate physical signs in real time using the device's camera, as a result of Google's acquisition of the Word Lens app. The original January launch only supported seven languages, but a July update added support for 20 new languages, and also enhanced the speed of Conversation Mode translations.
In May 2011, Google announced that the Google Translate API for software developers had been deprecated and would cease functioning. The Translate API page stated the reason as "substantial economic burden caused by extensive abuse" with an end date set for December 1, 2011. In response to public pressure, Google announced in June 2011 that the API would continue to be available as a paid service.
Because the API was used in numerous third-party websites and apps, the original decision to deprecate it led some developers to criticize Google and question the viability of using Google APIs in their products.
Google Translate also provides translations for Google Assistant and the devices that Google Assistant runs on such as Google Home and Google Pixel Buds.
The following languages are supported in Google Translate.
- 1st stage
- English to and from German
- English to and from Spanish
- English to and from French
- 2nd stage
- English to and from Portuguese
- 3rd stage
- English to and from Italian
- 4th stage
- English to and from Chinese (Simplified)
- English to and from Japanese
- English to and from Korean
- 5th stage (launched April 28, 2006)
- English to and from Arabic
- 6th stage (launched December 16, 2006)
- English to and from Russian
- 7th stage (launched February 9, 2007)
- English to and from Chinese (Traditional)
- Chinese (Simplified to and from Traditional)
- 8th stage (all 25 language pairs use Google's machine translation system) (launched October 22, 2007)
- English to and from Dutch
- English to and from Greek
- 9th stage
- English to and from Hindi
- 10th stage (as of this stage, translation can be done between any two languages, using English as an intermediate step, if needed) (launched May 8, 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 transliterated to the native script for these languages as the user is typing. The text can now be read by a text-to-speech program in English, Italian, French and German.
- 16th stage (launched January 30, 2010)
- Haitian Creole
- 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 on eSpeak)
- 19th stage (launched May 13, 2010)
- 20th stage (launched June 2010)
- Provides romanization for Arabic.
- 21st stage (launched September 2010)
- Allows phonetic typing for Arabic, Greek, Hindi, Persian, Russian, Serbian and Urdu.
- 22nd stage (launched December 2010)
- Romanization of Arabic removed.
- Spell check added.
- For some languages, Google replaced text-to-speech synthesizers from eSpeak's robot voice to native speaker's nature voice technologies made by SVOX (Chinese, Czech, Danish, Dutch, Finnish, Greek, Hungarian, Norwegian, Polish, Portuguese, Russian, Swedish, Turkish). Also the old versions of French, German, Italian and Spanish. Latin uses the same synthesizer as Italian.
- Speech program launched in Arabic, Japanese and Korean.
- 23rd stage (launched January 2011)
- Choice of different translations for a word.
- 24th stage (launched June 2011)
- 5 new Indic languages (in alpha) and a transliterated input method:
- 25th stage (launched July 2011)
- Translation rating introduced.
- 26th stage (launched January 2012)
- Dutch male voice synthesizer replaced with female.
- Elena by SVOX replaced the Slovak eSpeak voice.
- Transliteration of Yiddish added.
- 27th stage (launched February 2012)
- Speech program launched in Thai.
- 28th stage (launched September 2012)
- 29th stage (launched October 2012)
- Transliteration of Lao added. (alpha status)
- 30th stage (launched October 2012)
- New speech program launched in English.
- 31st stage (launched November 2012)
- New speech program in French, Spanish, Italian and German.
- 32nd stage (launched March 2013)
- Phrasebook added.
- 33rd stage (launched April 2013)
- 34th stage (launched May 2013)
- 35th stage (launched May 2013)
- 16 additional languages can be used with camera-input: Bulgarian, Catalan, Croatian, Danish, Estonian, Finnish, Hungarian, Indonesian, Icelandic, Latvian, Lithuanian, Norwegian, Romanian, Slovak, Slovenian and Swedish.
- 36th stage (launched December 2013)
- 37th stage (launched June 2014)
- Definition of words added.
- 38th stage (launched December 2014)
- 39th stage (launched October 2015)
- Transliteration of Arabic restored.
- 40th stage (launched November 2015)
- 41st stage (launched February 2016)
- 13 more languages (Sindhi, Pashto, Amharic, Corsican, Frisian, Kyrgyz, Hawaiian, Kurdish (Kurmanji), Luxembourgish, Samoan, Scots Gaelic, Shona and Xhosa) were added into Google Translate.
- Aurebesh removed.
- Speech program launched in Bengali.
- Kurdish (Kurmanji)
- Scottish Gaelic
- West Frisian
- 42nd stage (launched September 2016)
- Speech program launched in Ukrainian.
- 43rd stage (launched December 2016)
- Speech program launched in Khmer and Sinhala.
Method of translation
In April 2006, Google Translate launched with a statistical machine translation engine.
Google Translate does not apply grammatical rules, since its algorithms are based on statistical analysis rather than traditional rule-based analysis. The system's original creator, Franz Josef Och, has criticized the effectiveness of rule-based algorithms in favor of statistical approaches. It is based on a method called statistical machine translation, and more specifically, on research by Och who won the DARPA contest for speed machine translation in 2003. Och was the head of Google's machine translation group until leaving to join Human Longevity, Inc. in July 2014.
According to Och, a solid base for developing a usable statistical machine translation system for a new pair of languages from scratch would consist of a bilingual text corpus (or parallel collection) of more than 150-200 million words, and two monolingual corpora each of more than a billion words. Statistical models from these data are then used to translate between those languages.
To acquire this huge amount of linguistic data, Google used United Nations and European Parliament transcripts.
Google Translate does not translate from one language to another (L1 -> L2). Instead, it often translates first to English and then to the target language (L1 -> EN -> L2).
When Google Translate generates a translation, it looks for patterns in hundreds of millions of documents to help decide on the best translation. By detecting patterns in documents that have already been translated by human translators, Google Translate makes intelligent guesses as to what an appropriate translation should be.
Before October 2007, for languages other than Arabic, Chinese and Russian, Google Translate was based on SYSTRAN, a software engine which is still used by several other online translation services such as Babel Fish (now defunct). Since October 2007, Google Translate has used proprietary, in-house technology based on statistical machine translation instead.
Google Neural Machine Translation
In September 2016, a research team at Google led by the software engineer Harold Gilchrist announced the development of the Google Neural Machine Translation system (GNMT) to increase fluency and accuracy in Google Translate and in November announced that Google Translate would switch to GNMT. (wikipedia)
Google Translate's neural machine translation system uses a large end-to-end artificial neural network capable of deep learning, in particular, long short-term memory networks.
GNMT improves the quality of translation because it uses an example-based machine translation (EBMT) method in which the system "learns from millions of examples." It translates "whole sentences at a time, rather than just piece by piece. It uses this broader context to help it figure out the most relevant translation, which it then rearranges and adjusts to be more like a human speaking with proper grammar". GNMT's "proposed architecture" of "system learning" was first tested on over a hundred languages supported by Google Translate. With the end-to-end framework, "the system learns over time to create better, more natural translations." The GNMT network is capable of interlingual machine translation, which encodes the "semantics of the sentence rather than simply memorizing phrase-to-phrase translations", and the system did not invent its own universal language, but uses "the commonality found inbetween many languages". GNMT was first enabled for eight languages: to and from English and Chinese, French, German, Japanese, Korean, Portuguese, Spanish and Turkish. In March 2017, it was enabled for Hindi, Russian and Vietnamese languages, followed by Indonesian, Bengali, Gujarati, Kannada, Malayalam, Marathi, Punjabi, Tamil and Telugu languages in April.
GNMT has the capability to translate directly from one language to another (L1 -> L2), which improves upon the previous versions of Google Translate which first translated to English and then to the target language (L1 -> EN -> L2). The GNMT system is also capable of Zero-Shot Translation - translating between a language pair (for example, Japanese to Korean) which the "system has never explicitly seen before."
In 2014, Google launched "Translate Community", a platform aimed at improving the translation service by seeking help from volunteers. In August 2016, a Google Crowdsource app was released for Android users, in which translation tasks are offered.
Some languages produce better results than others. Google Translate performs well especially when English is the target language and the source language is from the European Union due to the prominence of translated EU parliament notes. A 2010 analysis indicated that French to English translation is relatively accurate. However, if the source text is shorter, rule-based machine translations often perform better; this effect is particularly evident in Chinese to English translations. While edits of translations may be submitted, in Chinese specifically one is not able to edit sentences as a whole. Instead, one must edit sometimes arbitrary sets of characters, leading to incorrect edits.
Shortly after launching the translation service for the first time, Google won an international competition for English-Arabic and English-Chinese machine translation.
Translation mistakes and oddities
Since Google Translate used statistical matching to translate, translated text can often include apparently nonsensical and obvious errors, sometimes swapping common terms for similar but nonequivalent common terms in the other language, or inverting sentence meaning. Novelty websites like Bad Translator and Translation Party have utilized the service to produce humorous text by translating back and forth between multiple languages, similar to the children's game Chinese whispers.
In 2017, Google Translate was used during a court hearing when court officials at Teesside Magistrates' Court failed to book an interpreter for a Chinese defendant.
- ^ a b Orch, Franz (April 28, 2006). "Statistical machine translation live". Google Research Blog. Google. Retrieved 2016.
- ^ a b c d e f Turovsky, Barak (November 15, 2016). "Found in translation: More accurate, fluent sentences in Google Translate". The Keyword Google Blog. Google. Retrieved 2017.
- ^ "About - Google Translate". Google. Retrieved 2017.
- ^ "Google Translate Help". Google Translate Help. Google. Retrieved 2016.
- ^ a b "See which features work with each language". Google. Retrieved 2017.
- ^ Shankland, Stephen (May 18, 2013). "Google Translate now serves 200 million people daily". CNET. CBS Interactive. Retrieved 2016.
- ^ "Translate written words". Google Translate Help. Google. Retrieved 2016.
- ^ "Translate text messages, webpages, or documents". Google Translate Help. Google. Retrieved 2016.
- ^ "Save translations in a phrasebook". Google Translate Help. Google. Retrieved 2017.
- ^ "Translate with handwriting or virtual keyboard". Google Translate Help. Google. Retrieved 2016.
- ^ "Translate by speech". Google Translate Help. Google. Retrieved 2016.
- ^ Baldwin, Roberto (October 16, 2014). "Google introduces Google Translate Chrome Extension for inline translations of text". The Next Web. Retrieved 2017.
- ^ Wauters, Robin (February 14, 2010). "Rant: Google Translate Toolbar In Chrome 5 Needs An 'Off' Button". TechCrunch. AOL. Retrieved 2017.
- ^ "Google Translate APKs - APKMirror". APKMirror. Android Police. Retrieved 2018.
- ^ "Google Translate on the App Store". App Store. Apple Inc. Retrieved 2018.
- ^ Setalvad, Ariha (July 29, 2015). "Google Translate adds 20 new languages to video text translation". The Verge. Vox Media. Retrieved 2017.
- ^ Zhu, Wenzhang (February 8, 2011). "Introducing the Google Translate app for iPhone". Official Google Blog. Google. Retrieved 2017.
- ^ Hachman, Mark (January 12, 2011). "Google Translate's New 'Conversation Mode': Hands On". PC Magazine. Ziff Davis. Retrieved 2017.
- ^ Velazco, Chris (October 13, 2011). "Google Translate For Android Gets Upgraded "Conversation Mode"". TechCrunch. AOL. Retrieved 2017.
- ^ Russell, Jon (January 14, 2015). "Google Translate Now Does Real-Time Voice And Sign Translations On Mobile". TechCrunch. AOL. Retrieved 2017.
- ^ Petrovan, Bogdan (January 14, 2015). "Google Translate just got smarter: Word Lens and instant voice translations in latest update". Android Authority. Retrieved 2017.
- ^ Gush, Andrew (July 29, 2015). "Google Translate adds video translation support for 25 more languages". Android Authority. Retrieved 2017.
- ^ Olanoff, Drew (July 29, 2015). "Google Translate's App Now Instantly Translates Printed Text In 27 Languages". TechCrunch. AOL. Retrieved 2017.
- ^ Feldman, Adam (May 26, 2011). "Spring cleaning for some of our APIs". Official Google Code Blog. Google. Archived from the original on May 28, 2011. Retrieved 2016.
- ^ "Google Translate API (Deprecated)". Google Code. Google. Archived from the original on August 22, 2011. Retrieved 2016.
- ^ Feldman, Adam (June 3, 2011). "Spring cleaning for some of our APIs". Official Google Code Blog. Google. Retrieved 2016.
- ^ Burnette, Ed (May 27, 2011). "Google pulls the rug out from under web service API developers, nixes Google Translate and 17 others". ZDNet. CBS Interactive. Retrieved 2016.
- ^ Wong, George (May 27, 2011). "Google gets rid of APIs for Translate and other services". UberGizmo. Retrieved 2016.
- ^ Statistical machine translation live, Franz Josef Och, Google Research Blog, April 28, 2006
- ^ Henderson, Fergus (November 5, 2010). "Giving a voice to more languages on Google Translate". Google Blog. Retrieved 2011.
- ^ "Five more languages on Google Translate". Google Translate Blog. May 13, 2010. Retrieved 2011.
- ^ Jakob Uszkoreit, Ingeniarius Programmandi (September 30, 2010). "Veni, Vidi, Verba Verti". Google Blog. Retrieved 2011.
- ^ SVOX Archived December 26, 2010, at the Wayback Machine.
- ^ "Google Translate welcomes you to the Indic web". Google Translate Blog.
- ^ Google Translate Blog: Tutmonda helplingvo por ?iuj homoj
- ^ Brants, Thorsten (September 13, 2012). "Translating Lao". Google Translate Blog. Retrieved 2012.
- ^ Crum, Chris (September 13, 2012). "Google Adds its 65th Language to Google Translate with Lao". WebProNews. Retrieved 2012.
- ^ Bell, Lee (February 18, 2016). "Google Translate app now lets 99% of world population translate speech". Mail Online. Retrieved 2016.
- ^ "Google adds Sindhi to its translate language options | Latest News & Updates at Daily News & Analysis". DNA India. Diligent Media Corporation Ltd. February 18, 2016. Retrieved 2016.
- ^ "Google adds Sindhi to its translate language options". Yahoo! News. Asian News International. February 18, 2016. Retrieved 2016.
- ^ Ahmed, Ali (February 18, 2016). "Google Translate now includes Sindhi and Pashto". Business Recorder. Retrieved 2016.
- ^ "Google can now translate text into Sindhi, Pashto and vice versa". Dawn. February 19, 2016. Retrieved 2016.
- ^ a b Och, Franz (September 12, 2005). "Statistical Machine Translation: Foundations and Recent Advances" (PDF). Google. Retrieved 2016.
- ^ "Franz Och, Ph.D., Expert in Machine Learning and Machine Translation, Joins Human Longevity, Inc. as Chief Data Scientist" (Press release). La Jolla, CA: Human Longevity, Inc. July 29, 2014. Retrieved 2015.
- ^ Adams, Tim (December 19, 2010). "Can Google break the computer language barrier?". The Guardian. Guardian Media Group. Retrieved 2017.
- ^ Tanner, Adam (March 28, 2007). "Google seeks world of instant translations". Reuters. Thomson Reuters. Retrieved 2017.
- ^ Boitet, Christian; Blanchon, Hervé; Seligman, Mark; Bellynck, Valérie. "MT on and for the Web" (PDF). Retrieved 2016.
- ^ "Inside Google Translate". Google. Archived from the original on August 22, 2010. Retrieved 2016.
- ^ Chitu, Alex (October 22, 2007). "Google Switches to Its Own Translation System". Unofficial Google Blog. Retrieved 2017.
- ^ Schwartz, Barry (October 23, 2007). "Google Translate Drops Systran For Home Brewed Translation". Search Engine Land. Retrieved 2017.
- ^ a b Le, Quoc; Schuster, Mike (September 27, 2016). "A Neural Network for Machine Translation, at Production Scale". Google Research Blog. Google. Retrieved 2016.
- ^ a b c d e Schuster, Mike; Johnson, Melvin; Thorat, Nikhil (November 22, 2016). "Zero-Shot Translation with Google's Multilingual Neural Machine Translation System". Google Research Blog. Google. Retrieved 2017.
- ^ Sepp Hochreiter; Jürgen Schmidhuber (1997). "Long short-term memory". Neural Computation. 9 (8): 1735-1780. doi:10.1162/neco.19220.127.116.115. PMID 9377276.
- ^ Felix A. Gers; Jürgen Schmidhuber; Fred Cummins (2000). "Learning to Forget: Continual Prediction with LSTM". Neural Computation. 12 (10): 2451-2471. doi:10.1162/089976600300015015.
- ^ Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation (26 Sep 2016):
Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V. Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, Jeff Klingner, Apurva Shah, Melvin Johnson, Xiaobing Liu, ?ukasz Kaiser, Stephan Gouws, Yoshikiyo Kato, Taku Kudo, Hideto Kazawa, Keith Stevens, George Kurian, Nishant Patil, Wei Wang, Cliff Young, Jason Smith, Jason Riesa, Alex Rudnick, Oriol Vinyals, Greg Corrado, Macduff Hughes, Jeffrey Dean. https://arxiv.org/abs/1609.08144
- ^ "An Infusion of AI Makes Google Translate More Powerful Than Ever." Cade Metz, WIRED, Date of Publication: 09.27.16. https://www.wired.com/2016/09/google-claims-ai-breakthrough-machine-translation/
- ^ a b Boitet, Christian; Blanchon, Hervé; Seligman, Mark; Bellynck, Valérie (2010). "MT on and for the Web" (PDF). Retrieved 2016.
- ^ McDonald, Chris (January 7, 2017). "Ok slow down". Medium. Retrieved 2017.
- ^ Davenport, Corbin (March 6, 2017). "Google Translate now uses neural machine translation for some languages". Android Police. Retrieved 2017.
- ^ Hager, Ryne (April 25, 2017). "Google adds Indonesian and eight new Indian languages to its neural machine translation". Android Police. Retrieved 2017.
- ^ Lardinois, Frederic (July 25, 2014). "Google Wants To Improve Its Translations Through Crowdsourcing". TechCrunch. AOL. Retrieved 2017.
- ^ Summers, Nick (July 25, 2014). "Google sets up a community site to help improve Google Translate". The Next Web. Retrieved 2017.
- ^ Whitwam, Ryan (August 29, 2016). "New Google Crowdsource app asks you to help with translation and text transcription a few seconds at a time". Android Police. Retrieved 2017.
- ^ Shankland, Stephen (August 29, 2016). "New Crowdsource app lets you work for Google for free". CNET. CBS Interactive. Retrieved 2017.
- ^ a b Ethan Shen, Comparison of online machine translation tools, archived from the original on February 10, 2011, retrieved 2010
- ^ Nielsen, Michael. Reinventing discovery: the new era of networked science. Princeton, NJ: Princeton University Press. p. 125. ISBN 978-0-691-14890-8.
- ^ Gomes, Lee (July 22, 2010). "Google Translate Tangles With Computer Learning". Forbes. Retrieved 2017.
- ^ Weinberg, Nathan (September 10, 2007). "Google Translates Ivan the Terrible as "Abraham Lincoln"". Blog News Channel. Archived from the original on September 12, 2007. Retrieved 2017.
- ^ Kincaid, Jason (August 7, 2009). "Translation Party: Tapping Into Google Translate's Untold Creative Genius". TechCrunch. AOL. Retrieved 2017.
- ^ "A British court was forced to rely on Google Translate because it had no interpreter". Business Insider. Retrieved 2017.