Type of site
|Available in||103 languages, see below|
|Users||Over 200+ million people daily|
|Launched||April 28, 2006statistical machine translation)
November 15, 2016 (as neural machine translation)
Google Translate is a free multilingual machine translation service developed by Google, to translate text, speech, images, sites, or real-time video from one language into another. It offers a web 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 2013, serves over 200 million people daily.
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". GNMT was first enabled for eight languages: to and from English and Chinese, French, German, Japanese, Korean, Portuguese, Spanish and Turkish.
- 1 Features
- 2 Supported languages
- 3 Method of translation
- 4 Limitations
- 5 Open-source licenses and components
- 6 Reviews
- 7 Translate Community
- 8 See also
- 9 References
- 10 External links
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.
Google Translate is available in some browsers as an extension which can run the translation engine.
The Google Translate app for Android and iOS supports more than 90 languages and can translate 37 languages via photo, 32 via voice in "conversation mode", and 27 via real-time video in "augmented reality mode".
An early 2011 version supported Conversation Mode when translating between English and Spanish (in alpha testing). This interface within Google Translate allows users to communicate fluidly with a nearby person in another language. In October 2011 it was expanded to 14 languages.
The 'Camera input' functionality allows users to take a photograph of a document, signboard, etc. Google Translate recognises the text from the image using optical character recognition (OCR) technology and gives the translation. Camera input is not available for all languages.
In January 2015, the application gained the ability to translate text in real time using the device's camera, as a result of Google's acquisition of the Word Lens app. The speed and quality of real-time video translation (augmented reality) feature were further enhanced in July 2015 with the release of a new implementation that utilizes convolutional neural networks.
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.
The following languages are supported in Google Translate.
- Chinese (Simplified and Traditional)
- Haitian Creole
- Kurdish (Kurmanji)
- Myanmar (Burmese)
- Scots Gaelic
Languages in development
These languages are not yet supported by Google Translate, but are available in the Translate Community.
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 documents. The UN typically publishes documents in all six official UN languages, which has produced a very large 6-language corpus.
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 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.
Google Translate's new neural machine translation system uses a large end-to-end artificial neural network capable of deep learning. GNMT improves the quality of translation because it uses an example based (EBMT) machine translation 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.
GNMT is an improvement on Google Translate in that it is capable of translating directly from one language to another (L1 → L2) instead often first translating to English, for example, and then to the target language (L1 → EN → L2). The GNMT system is "capable of Zero-Shot Translation - translating between a language pair (for example, Japanese to Korean) which the "system has never explicitly seen before." Previously, Google Translate translated to English and then to the target language (L1 → EN → L2) not directly from one language to another (L1 → L2).
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.
Texts written in the Greek, Devanagari, Cyrillic and Arabic scripts can be transliterated automatically from phonetic equivalents written in the Latin alphabet. The browser version of Google Translate provides the read phonetically option for Japanese to English conversion. The same option is not available on the paid API version.
Many of the more popular languages have a "text-to-speech" audio function that is able to read back a text in that language, up to a few dozen words or so. In the case of pluricentric languages, the accent depends on the region: for English, in the Americas, most of the Asia-Pacific and West Asia the audio uses a female General American accent, whereas in Europe, Hong Kong, Malaysia, Singapore, Guyana and all other parts of the world a female British English accent is used, except for a special Oceania accent used in Australia, New Zealand and Norfolk Island; for Spanish, in the Americas a Latin American Spanish accent is used, while in the other parts of the world a Castilian Spanish accent is used; Portuguese uses a São Paulo accent in the world, except for Portugal, where their native accent is used. Some less widely spoken languages use the open-source eSpeak synthesizer for their speech.
Open-source licenses and components
|Albanian||Albanet||CC-BY 3.0/GPL 3|
|Arabic||Arabic Wordnet||CC-BY-SA 3|
|Catalan||Multilingual Central Repository||CC-BY-3.0|
|French||WOLF (WOrdnet Libre du Français)||CeCILL-C|
|Galician||Multilingual Central Repository||CC-BY-3.0|
|Hindi||IIT Bombay Wordnet||Indo Wordnet|
|Persian||Persian Wordnet||Free to Use|
|Spanish||Multilingual Central Repository||CC-BY-3.0|
Shortly after launching the translation service, Google won an international competition for English–Arabic and English–Chinese machine translation.
Translation mistakes and oddities
Since Google Translate uses 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.
Translate Community is a platform intended to improve the Google Translate service. Volunteers can select up to five languages to help improve translation; users can verify translated phrases and translate phrases in their languages to and from English, helping to improve the accuracy of translating more rare and complex phrases. In August 2016 the Google Crowdsource app was released, which also offered translation tasks.
- Babel Fish (discontinued; redirects to main Yahoo! site)
- Comparison of machine translation applications
- Google Dictionary (discontinued)
- Google Text-to-Speech
- Google Translator Toolkit
- Jollo (discontinued)
- List of Google products
- Microsoft Translator
- Omniscien Technologies
- Word Lens (discontinued; merged into Google Translate app)
- Orch, Franz (April 28, 2006). "Statistical machine translation live". Google Research Blog. Google. Retrieved December 1, 2016.
- Turovsky, Barak (November 15, 2016). "Found in translation: More accurate, fluent sentences in Google Translate". The Keyword Google Blog. Google. Retrieved March 23, 2017.
- "Languages - Google Translate". Google. Retrieved October 15, 2016.
- Shankland, Stephen (May 18, 2013). "Google Translate now serves 200 million people daily". CNET. CBS Interactive. Retrieved December 1, 2016.
- Le, Quoc; Schuster, Mike (September 27, 2016). "A Neural Network for Machine Translation, at Production Scale". Google Research Blog. Google. Retrieved December 1, 2016.
- "About - Google Translate". Google. Retrieved December 1, 2016.
- "Google Translate Help". Google Translate Help. Google. Retrieved December 1, 2016.
- "Translate written words". Google Translate Help. Google. Retrieved December 1, 2016.
- "Translate text messages, webpages, or documents". Google Translate Help. Google. Retrieved December 1, 2016.
- "Translate with handwriting or virtual keyboard". Google Translate Help. Google. Retrieved December 1, 2016.
- "Translate by speech". Google Translate Help. Google. Retrieved December 1, 2016.
- "Search Add-ons :: Add-ons for Firefox". Mozilla. Retrieved August 7, 2009.
- "Google Translate". Chrome Web Store. Google. Retrieved December 1, 2016.
- Brinkmann, Martin (February 7, 2010). "Google Translate Integrated In Google Chrome 5". Ghacks.net. Retrieved December 1, 2016.
- Setalvad, Ariha (July 29, 2015). "Google Translate adds 20 new languages to video text translation". The Verge. Vox Media. Retrieved March 23, 2017.
- Hutchison, Allen (August 7, 2008). "Google Translate now for iPhone". Google Mobile Blog. Google. Retrieved March 23, 2017.
- Zhu, Wenzhang (February 8, 2011). "Introducing the Google Translate app for iPhone". Official Google Blog. Google. Retrieved March 23, 2017.
- Ryan Kim (October 13, 2011). "Google Translate conversation mode expands to 14 languages". GigaOM.
- Turovsky, Barak (January 14, 2015). "Hallo, hola, olá to the new, more powerful Google Translate app". Official Google Blog. Google. Retrieved March 23, 2017.
- Turovsky, Barak (July 29, 2015). "See the world in your language with Google Translate". Official Google Blog. Google. Retrieved March 23, 2017.
- Good, Otavio (July 29, 2015). "How Google Translate squeezes deep learning onto a phone". Google Research Blog. Google. Retrieved March 23, 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 December 11, 2016.
- "Google Translate API (Deprecated)". Google Code. Google. Archived from the original on August 22, 2011. Retrieved December 11, 2016.
- Feldman, Adam (June 3, 2011). "Spring cleaning for some of our APIs". Official Google Code Blog. Google. Retrieved December 11, 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 December 11, 2016.
- Wong, George (May 27, 2011). "Google gets rid of APIs for Translate and other services". UberGizmo. Retrieved December 11, 2016.
- "See which features work with each language". Google. Retrieved January 11, 2017.
- "Translate Community: Help us improve Google Translate!".
- Och, Franz (September 12, 2005). "Statistical Machine Translation: Foundations and Recent Advances" (PDF). Google. Retrieved December 1, 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 January 15, 2015.
- "Google seeks world of instant translations". ABC News. Retrieved November 8, 2015.
- Boitet, Christian; Blanchon, Hervé; Seligman, Mark; Bellynck, Valérie. "MT on and for the Web" (PDF). Retrieved December 1, 2016.
- "Inside Google Translate". Google. Archived from the original on August 22, 2010. Retrieved December 11, 2016.
- Chitu, Alex (October 22, 2007). "Google Switches to Its Own Translation System". Unofficial Google Blog. Retrieved March 23, 2017.
- Schwartz, Barry (October 23, 2007). "Google Translate Drops Systran For Home Brewed Translation". Search Engine Land. Retrieved March 23, 2017.
- 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 March 23, 2017.
- Boitet, Christian; Blanchon, Hervé; Seligman, Mark; Bellynck, Valérie (2010). "MT on and for the Web" (PDF). Retrieved December 1, 2016.
- McDonald, Chris (January 7, 2017). "Ok slow down". Medium. Retrieved March 23, 2017.
- Ethan Shen, Comparison of online machine translation tools, archived from the original on February 10, 2011, retrieved December 15, 2010
- "Inside Google Translate". Google. Archived from the original on January 1, 2014. Retrieved December 11, 2016.
- 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 March 23, 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 March 23, 2017.
- Kincaid, Jason (August 7, 2009). "Translation Party: Tapping Into Google Translate's Untold Creative Genius". TechCrunch. AOL. Retrieved March 23, 2017.
- "Translate Community FAQ". Google.
- 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 March 23, 2017.