Software:Google Translate

From HandWiki
Revision as of 08:22, 9 February 2024 by QCDvac (talk | contribs) (add)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Short description: Multilingual neural machine translation service
Google Translate
Google Translate logo.svg
Google Translate screenshot.png
Google Translate website homepage
Type of site
Neural machine translation
Available inGoogle Translate languages; see below
OwnerGoogle
Websitetranslate.google.com
CommercialYes
RegistrationOptional
UsersOver 610 million people daily
Current statusActive

Google Translate is a multilingual neural machine translation service developed by Google to translate text, documents and websites from one language into another. It offers a website interface, a mobile app for Android and iOS, as well as an API that helps developers build browser extensions and software applications.[1] As of 2022, Google Translate supports Google Translate languages at various levels;[2] it claimed over 500 million total users (As of April 2016),[3] with more than 100 billion words translated daily, after the company stated in May 2013 that it served over 200 million people daily.[4]

Launched in April 2006 as a statistical machine translation service, it used United Nations and European Parliament documents and transcripts to gather linguistic data. Rather than translating languages directly, it first translates text to English and then pivots to the target language in most of the language combinations it posits in its grid,[5] with a few exceptions including Catalan–Spanish.[6] During a translation, it looks for patterns in millions of documents to help decide which words to choose and how to arrange them in the target language. Its accuracy, which has been criticized on several occasions,[7] has been measured to vary greatly across languages.[8] 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".[9]

History

Google Translate is a web-based free-to-user translation service developed by Google in April 2006.[10] It translates multiple forms of texts and media such as words, phrases and webpages.

Originally, Google Translate was released as a statistical machine translation service.[10] The input text had to be translated into English first before being translated into the selected language.[10] Since SMT uses predictive algorithms to translate text, it had poor grammatical accuracy. Despite this, Google initially did not hire experts to resolve this limitation due to the ever-evolving nature of language.[10]

In January 2010, Google introduced an Android app and iOS version in February 2011 to serve as a portable personal interpreter.[10] As of February 2010, it was integrated into browsers such as Chrome and was able to pronounce the translated text, automatically recognize words in a picture and spot unfamiliar text and languages.[10]

In May 2014, Google acquired Word Lens to improve the quality of visual and voice translation.[11] It is able to scan text or a picture using the device and have it translated instantly. Moreover, the system automatically identifies foreign languages and translates speech without requiring individuals to tap the microphone button whenever speech translation is needed.[11]

In November 2016, Google transitioned its translating method to a system called neural machine translation.[12] It uses deep learning techniques to translate whole sentences at a time, which has been measured to be more accurate between English and French, German, Spanish, and Chinese.Cite error: Closing </ref> missing for <ref> tag

At the end of September 2022, Google Translate was discontinued in mainland China, which Google said was due to "low usage".[13][14]

Functions

Google Translate can translate multiple forms of text and media, which includes text, speech, and text within still or moving images.[15][16] Specifically, its functions include:

  • Written Words Translation: a function that translates written words or text to a foreign language.[17]
  • Website Translation: a function that translates a whole webpage to selected languages.[18]
  • Document Translation: a function that translates a document uploaded by the users to selected languages. The documents should be in the form of: .doc, .docx, .odf, .pdf, .ppt, .pptx, .ps, .rtf, .txt, .xls, .xlsx.[18]
  • Speech Translation: a function that instantly translates spoken language into the selected foreign language.[19]
  • Mobile App Translation: in 2018, Google introduced its new Google Translate feature called "Tap to Translate", which made instant translation accessible inside any app without exiting or switching it.[20]
  • Image Translation: a function that identifies text in a picture taken by the users and translates text on the screen instantly by images.[21]
  • Handwritten Translation: a function that translates language that are handwritten on the phone screen or drawn on a virtual keyboard without the support of a keyboard.[22]
  • Bilingual Conversation Translation: a function that translates conversations in multiple languages.[23]
  • Transcription: a function that transcribes speech in different languages.[24]

For most of its features, Google Translate provides the pronunciation, dictionary, and listening to translation. Additionally, Google Translate has introduced its own Translate app, so translation is available with a mobile phone in offline mode.[15][16]

Features

English Wikipedia's homepage translated into Portuguese

Web interface

Google Translate produces approximations across languages of multiple forms of text and media, including text, speech, websites, or text on display in still or live video images! [15][16] For some languages, Google Translate can synthesize speech from text,[17] and in certain pairs it is possible to highlight specific corresponding words and phrases between the source and target text. Results are sometimes shown with dictional information below the translation box, but it is not a dictionary[25] and has been shown to invent translations in all languages for words it does not recognize.[26] If "Detect language" is selected, text in an unknown language can be automatically identified. In the web interface, users can suggest alternate translations, such as for technical terms, or correct mistakes. These suggestions may be included in future updates to the translation process. If a user enters a URL in the source text, Google Translate will produce a hyperlink to a machine translation of the website.[18] Users can save translation proposals in a "phrasebook" for later use, and a shareable URL is generated for each translation.[27][28] For some languages, text can be entered via an on-screen keyboard, through handwriting recognition, or speech recognition.[22][19] It is possible to enter searches in a source language that are first translated to a destination language allowing one to browse and interpret results from the selected destination language in the source language.

Texts written in the Arabic, Cyrillic, Devanagari and Greek scripts can be transliterated automatically from phonetic equivalents written in the Latin alphabet. The browser version of Google Translate provides the option to show phonetic equivalents of text translated from Japanese to English. The same option is not available on the paid API version.

Accent of English that the "text-to-speech" audio of Google Translate of each country uses:
  British (Received Pronunciation) (female)
  General American (female)
  General Australian (female)
  Indian (female)
  No Google translate service

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 several hundred 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 Western 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 (Received Pronunciation) accent is used, except for a special General Australian accent used in Australia, New Zealand and Norfolk Island, and an Indian English accent used in India; for Spanish, in the Americas, a Latin American accent is used, while in other parts of the world, a Castilian accent is used; for Portuguese, a São Paulo accent is used around the world, except in Portugal, where their native accent is used instead; for French, a Quebec accent is used in Canada, while in other parts of the world, a standard European accent is used; for Bengali, a male Bangladeshi accent is used, except in India, where a special female Indian Bengali accent is used instead. Until March 2023, some less widely spoken languages used the open-source eSpeak synthesizer for their speech; producing a robotic, awkward voice that may be difficult to understand.

Browser integration

Google Translate is available in some web browsers as an optional downloadable extension that can run the translation engine, which allow right-click command access to the translation service.[29][30][31] In February 2010, Google Translate was integrated into the Google Chrome browser by default, for optional automatic webpage translation.[32][33][34]

Mobile app

Google Translate
Google Translate logo.svg
Screenshot
Google Translate for Android screenshot.png
A screenshot of the Android app of Google Translate
Developer(s)Google
Initial releaseJanuary 1, 2010; 14 years ago (2010-01-01) (for Android)
February 8, 2011; 13 years ago (2011-02-08) (for iOS)
Stable release(s) [±]
Android6.35.29.444893127.4 / April 28, 2022; 2 years ago (2022-04-28)[35]
iOS6.34.0 / April 19, 2022; 2 years ago (2022-04-19)[36]
Platform
Size37.44 MB (Android)
123.7 MB (iOS)
Available inGoogle Translate languages; see below
TypeNeural machine translation
Websitetranslate.google.com/m?hl=en

The Google Translate app for Android and iOS supports Google Translate languages and can propose translations for 37 languages via photo, 32 via voice in "conversation mode", and 27 via live video imagery in "augmented reality mode".[37][38]

The Android app was released in January 2010, and for iOS on February 8, 2011,[39] after an HTML5 web application was released for iOS users in August 2008.[40] The Android app is compatible with devices running at least Android 2.1, while the iOS app is compatible with iPod Touches, iPads, and iPhones updated to iOS 7.0+.[41]

A January 2011 Android version experimented with a "Conversation Mode" that aims to allow users to communicate fluidly with a nearby person in another language.[42] Originally limited to English and Spanish, the feature received support for 12 new languages, still in testing, the following October.[43][44]

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 apps gained the ability to propose translations of physical signs in real time using the device's camera, as a result of Google's acquisition of the Word Lens app.[45][46][11] The original January launch only supported seven languages, but a July update added support for 20 new languages, with the release of a new implementation that utilizes convolutional neural networks, and also enhanced the speed and quality of Conversation Mode translations (augmented reality).[37][38][47][48][49] The feature was subsequently renamed Instant Camera. The technology underlying Instant Camera combines image processing and optical character recognition, then attempts to produce cross-language equivalents using standard Google Translate estimations for the text as it is perceived.[50]

On May 11, 2016, Google introduced Tap to Translate for Google Translate for Android. Upon highlighting text in an app that is in a foreign language, Translate will pop up inside of the app and offer translations.[51]

API

On May 26, 2011, Google announced that the Google Translate API for software developers had been deprecated and would cease functioning.[52][53][54] The Translate API page stated the reason as "substantial economic burden caused by extensive abuse" with an end date set for December 1, 2011.[55] In response to public pressure, Google announced in June 2011 that the API would continue to be available as a paid service.[52][53][56]

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.[57][58]

Google Assistant

Google Translate also provides translations for Google Assistant and the devices that Google Assistant runs on such as Google Nest and Pixel Buds.

Supported languages

As of 2024, th lyinclude>133 languages are supported by Google Translate:[59]

Language Designation on
Google Translate
Support added Supports
voice input?
Supports
text-to-speech?
Afrikaans 2009 yes yes
Albanian 2009 yes yes
Amharic 2016[60] yes no
Arabic 2006 yes yes
Armenian 2010[61] yes no
Assamese 2022[2] no no
Aymara 2022[2] no no
Azerbaijani 2010[61] yes no
Bambara 2022[2] no no
Basque 2010[61] yes no
Belarusian 2009 no no
Bengali 2011 yes yes
Bhojpuri 2022[2] no no
Bosnian 2013[62] no yes
Bulgarian 2008 yes yes
Burmese Myanmar (Burmese) 2014[63] yes yes
Catalan 2008 yes yes
Cebuano 2013[62] no no
Chewa Chichewa 2014[63] no no
Chinese (Simplified) 2006 yes yes
Chinese (Traditional) 2007 yes yes
Corsican 2016[60] no no
Croatian 2006 yes yes
Czech 2006 yes yes
Danish 2006 yes yes
Dogri 2022[2] no no
Dutch 2006 yes yes
English 2006 yes yes
Esperanto 2012[64] no no
Estonian 2009 yes yes
Ewe 2022[2] no no
Filipino (Tagalog) Filipino 2008 yes yes
Finnish 2006 yes yes
French 2006 yes yes
Galician 2009 yes no
Georgian 2010[61] yes no
German 2006 yes yes
Greek 2006 yes yes
Guarani 2022[2] no no
Gujarati 2011 yes yes
Haitian Creole 2010 no no
Hausa 2013[65] no no
Hawaiian 2016[60] no no
Hebrew 2006 yes yes
Hindi 2006 yes yes
Hmong 2013[62] no no
Hungarian 2006 yes yes
Icelandic 2006 yes yes
Igbo 2013[65] no no
Ilocano 2022[2] no no
Indonesian 2006 yes yes
Irish 2009 no no
Italian 2006 yes yes
Japanese 2006 yes yes
Javanese 2013[62] yes yes
Kannada 2011 yes yes
Kazakh 2014[63] yes no
Khmer 2013[66] yes yes
Kinyarwanda 2020[67] yes no
Konkani 2022[2] no no
Korean 2006 yes yes
Krio 2022[2] no no
Kurdish (Kurmanji) 2016[60] no no
Kurdish (Sorani) 2022[2] no no
Kyrgyz 2016[60] no no
Lao 2012[68] yes no
Latin 2010 no yes
Latvian 2008 yes yes
Lingala 2022[2] no no
Lithuanian 2008 yes no
Luganda 2022[2] no no
Luxembourgish 2016[60] no no
Macedonian 2009 yes no
Maithili 2022[2] no no
Malagasy 2014[63] no no
Malay 2009 yes yes
Malayalam 2014[63] yes yes
Maldivian Dhivehi 2022[2] no no
Maltese 2009 no no
Māori Maori 2013[65] no no
Marathi 2013[62] yes yes
Meitei Meiteilon (Manipuri) 2022[2] no no
Mizo 2022[2] no no
Mongolian 2013[65] yes no
Nepali 2013[65] yes yes
Northern Sotho Sepedi 2022[2] yes no
Norwegian (Bokmål) Norwegian 2006 yes yes
Odia Odia (Oriya) 2020[67] no no
Oromo 2022[2] no no
Pashto 2016[60] no no
Persian 2009 yes no
Polish 2006 yes yes
Portuguese 2006 yes yes
Punjabi 2013[65] yes no
Romanian 2006 yes yes
Russian 2006 yes yes
Samoan 2016[60] no no
Sanskrit 2022 no no
Scottish Gaelic Scots Gaelic 2016[60] no no
Serbian 2008 yes yes
Shona 2016[60] no no
Sindhi 2016[60] no no
Sinhala 2014[63] yes yes
Slovak 2008 yes yes
Slovene Slovenian 2008 yes no
Somali 2013[65] no no
Sotho Sesotho 2014[63] yes no
Southern Quechua Quechua 2022[2] no no
Spanish 2006 yes yes
Sundanese 2014[63] yes yes
Swahili 2009 yes yes
Swedish 2006 yes yes
Tajik 2014[63] no no
Tamil 2011 yes yes
Tatar 2020[67] no no
Telugu 2011 yes yes
Thai 2006 yes yes
Tigrinya 2022[2] no no
Tsonga 2022[2] yes no
Turkish 2006 yes yes
Turkmen 2020[67] no no
Twi 2022[2] no no
Ukrainian 2006 yes yes
Urdu 2010[61] yes yes
Uyghur 2020[67] no no
Uzbek 2014[63] yes no
Vietnamese 2006 yes yes
Welsh 2009 no no
West Frisian Frisian 2016[60] no no
Xhosa 2016[60] yes no
Yiddish 2009 no no
Yoruba 2013[65] no no
Zulu 2013[65] yes no

Languages in development and beta version

The following languages are not yet supported by Google Translate, but are available in the Translate Community. As of November 2024, there are 103 languages in development, of which 9 are in beta version.[69]

The languages in beta version are closer to their public release and have an exclusive extra option to contribute that allows evaluating up to four translations of the beta version by translating an English text of up to 50 characters.

There is currently a petition for Google to add Cree to Google Translate, but as of November 2024, it is not one of the languages in development yet.[70][71]


  1. Acehnese (Achinese)
  2. Adyghe
  3. Afar BETA
  4. Aragonese
  5. Avar (Avaric)
  6. Bagheli
  7. Balochi (Baluchi)
  8. Bangala
  9. Baoulé
  10. Bashkir
  11. Berber (Tamazight) BETA
  12. Betawi
  13. Boro (India) (Bodo) BETA
  14. Breton
  15. Cantonese
  16. Chechen
  17. Cherokee
  18. Chhattisgarhi
  19. Chittagonian
  20. Chuvash
  21. Deccani
  22. Dholuo
  23. Dyula
  24. Dzongkha
  25. Edo
  26. Efik
  27. Esan
  28. Fon
  29. Fula (Fulfulde) BETA
  30. Gagauz
  31. Garhwali
  32. Greenlandic (Kalaallisut)
  33. Haryanvi
  34. Hiligaynon
  35. Inuktitut
  36. Isoko
  37. Kamba
  38. Kanuri
  39. Kapampangan (Pampanga)
  40. Karachay-Balkar
  41. Karakalpak (Kara-Kalpak)
  42. Kashmiri
  43. Kedah Malay
  44. Kelantan-Pattani Malay (Pattani Malay)
  45. Khakas
  46. Khandeshi (Ahirani)
  47. Khorasani Turkic
  48. Kikuyu
  49. Kokborok
  50. Kumyk
  51. Kʼicheʼ
  52. Lakota
  53. Lhasa Tibetan (Tibetan) BETA
  54. Luba-Kasai (Tshiluba)
  55. Luba-Katanga (Luba)
  56. Madurese
  57. Magahi
  58. Marwari
  59. Mazanderani
  60. Minangkabau
  61. Montenegrin
  62. Mooré (Mossi)
  63. Nagpuri (Sadri)
  64. Navajo
  65. Newar (Nepalbhasa) BETA
  66. Nigerian Pidgin
  67. Northern Sámi (Northern Sami)
  68. Occitan
  69. Qashqai
  70. Rajasthani
  71. Rangpuri
  72. Rohingya
  73. Romansh
  74. Salar
  75. Samogitian
  76. Sango
  77. Santali BETA
  78. Saraiki BETA
  79. Serrano
  80. Shor
  81. Siberian Tatar
  82. Sicilian
  83. Southern Altai
  84. Southern Ndebele
  85. Surjapuri
  86. Swahili Congo
  87. Sylheti
  88. Tiv
  89. Toba Batak (Batak Toba)
  90. Tok Pisin
  91. Tonga (Zambia and Zimbabwe) (Chitonga)
  92. Tswana (Setswana)
  93. Tswa
  94. Tuvan (Tuvinian)
  95. Urhobo
  96. Urum
  97. Varhadi (Varhadi-Nagpuri)
  98. Venda (Tshivenda)
  99. Wolof
  100. Yakut
  101. Yucatec Maya (Yucateco) BETA
  102. Zaza
  103. Zhuang


Translation methodology

In April 2006, Google Translate launched with a statistical machine translation engine.[72]

Google Translate does not apply grammatical rules, since its algorithms are based on statistical or pattern 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.[73][74] Original versions of Google Translate were 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.[75]

Google Translate does not directly translate from one language to another (L1 → L2). Instead, it often translates first to English and then to the target language (L1 → EN → L2).[76][77][78][5][79] However, because English, like all human languages, is ambiguous and depends on context, this can cause translation errors. For example, translating vous from French to Russian gives vous → you → ты OR Bы/вы.[80] If Google were using an unambiguous, artificial language as the intermediary, it would be vous → you → Bы/вы OR tu → thou → ты. Such a suffixing of words disambiguates their different meanings. Hence, publishing in English, using unambiguous words, providing context, using expressions such as "you all" may or may not make a better one-step translation depending on the target language.

The following languages do not have a direct Google translation to or from English. These languages are translated through the indicated intermediate language (which in most cases is closely related to the desired language but more widely spoken) in addition to through English:[citation needed]

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.[73] 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 documents and transcripts.[81][82] The UN typically publishes documents in all six official UN languages, which has produced a very large 6-language corpus.

Google representatives have been involved with domestic conferences in Japan where it has solicited bilingual data from researchers.[83]

When Google Translate generates a translation proposal, 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 informed guesses (AI) as to what an appropriate translation should be.[84]

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). From October 2007, Google Translate used proprietary, in-house technology based on statistical machine translation instead,[85][86] before transitioning to neural machine translation.

Google Translate Community

Google has crowdsourcing features for volunteers to be a part of its "Translate Community", intended to help improve Google Translate's accuracy.[87][88][89][90][91] 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.[92] In August 2016, a Google Crowdsource app was released for Android users, in which translation tasks are offered.[93][94] There are three ways to contribute. First, Google will show a phrase that one should type in the translated version.[89] Second, Google will show a proposed translation for a user to agree, disagree, or skip.[89] Third, users can suggest translations for phrases where they think they can improve on Google's results. Tests in 44 languages show that the "suggest an edit" feature led to an improvement in a maximum of 40% of cases over four years.[95]

Statistical machine translation

Although Google deployed a new system called neural machine translation for better quality translation, there are languages that still use the traditional translation method called statistical machine translation. It is a rule-based translation method that utilizes predictive algorithms to guess ways to translate texts in foreign languages. It aims to translate whole phrases rather than single words then gather overlapping phrases for translation. Moreover, it also analyzes bilingual text corpora to generate statistical model that translates texts from one language to another.[96][97]

Google Neural Machine Translation

Main page: 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[9][98] and in November announced that Google Translate would switch to GNMT.

Google Translate's neural machine translation system uses a large end-to-end artificial neural network that attempts to perform deep learning,[9][99][100] in particular, long short-term memory networks.[101][102][103][104] GNMT improves the quality of translation over SMT in some instances because it uses an example-based machine translation (EBMT) method in which the system "learns from millions of examples."[99] According to Google researchers, 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".[9] GNMT's "proposed architecture" of "system learning" has been implemented on over a hundred languages supported by Google Translate.[99] With the end-to-end framework, Google states but does not demonstrate for most languages that "the system learns over time to create better, more natural translations."[9] The GNMT network attempts interlingual machine translation, which encodes the "semantics of the sentence rather than simply memorizing phrase-to-phrase translations",[99][78] and the system did not invent its own universal language, but uses "the commonality found in between many languages".[105] GNMT was first enabled for eight languages: to and from English and Chinese, French, German, Japanese, Korean, Portuguese, Spanish and Turkish.[9][98] In March 2017, it was enabled for Hindi, Russian and Vietnamese,[106] followed by Bengali, Gujarati, Indonesian, Kannada, Malayalam, Marathi, Punjabi, Tamil and Telugu in April.[107]

Accuracy

Google Translate is not as reliable as human translation. When text is well-structured, written using formal language, with simple sentences, relating to formal topics for which training data is ample, it often produces conversions similar to human translations between English and a number of high-resource languages.[108][12] Accuracy decreases for those languages when fewer of those conditions apply, for example when sentence length increases or the text uses familiar or literary language. For many other languages vis-à-vis English, it can produce the gist of text in those formal circumstances.[109] Human evaluation from English to all 102 languages shows that the main idea of a text is conveyed more than 50% of the time for 35 languages. For 67 languages, a minimally comprehensible result is not achieved 50% of the time or greater.[8] A few studies have evaluated Chinese,[citation needed] French,[citation needed] German,[citation needed] and Spanish[citation needed] to English, but no systematic human evaluation has been conducted from most Google Translate languages to English. Speculative language-to-language scores extrapolated from English-to-other measurements[8] indicate that Google Translate will produce translation results that convey the gist of a text from one language to another more than half the time in about 1% of language pairs, where neither language is English.[110] Research conducted in 2011 showed that Google Translate got a slightly higher score than the UCLA minimum score for the English Proficiency Exam.[111] Due to its identical choice of words without considering the flexibility of choosing alternative words or expressions, it produces a relatively similar translation to human translation from the perspective of formality, referential cohesion, and conceptual cohesion.[112] Moreover, a number of languages are translated into a sentence structure and sentence length similar to a human translation.[112] Furthermore, Google carried out a test that required native speakers of each language to rate the translation on a scale between 0 and 6, and Google Translate scored 5.43 on average.[12]

When used as a dictionary to translate single words, Google Translate is highly inaccurate because it must guess between polysemic words. Among the top 100 words in the English language, which make up more than 50% of all written English, the average word has more than 15 senses,[113] which makes the odds against a correct translation about 15 to 1 if each sense maps to a different word in the target language. Most common English words have at least two senses, which produces 50/50 odds in the likely case that the target language uses different words for those different senses. The odds are similar from other languages to English. Google Translate makes statistical guesses that raise the likelihood of producing the most frequent sense of a word, with the consequence that an accurate translation will be unobtainable in cases that do not match the majority or plurality corpus occurrence. The accuracy of single-word predictions has not been measured for any language. Because almost all non-English language pairs pivot through English, the odds against obtaining accurate single-word translations from one non-English language to another can be estimated by multiplying the number of senses in the source language with the number of senses each of those terms have in English. When Google Translate does not have a word in its vocabulary, it makes up a result as part of its algorithm.[26]


Limitations

Google Translate, like other automatic translation tools, has its limitations. The service limits the number of paragraphs and the range of technical terms that can be translated, and while it can help the reader understand the general content of a foreign language text, it does not always deliver accurate translations, and most times it tends to repeat verbatim the same word it is expected to translate. Grammatically, for example, Google Translate struggles to differentiate between imperfect and perfect aspects in Romance languages so habitual and continuous acts in the past often become single historical events. Although seemingly pedantic, this can often lead to incorrect results (to a native speaker of for example French and Spanish) which would have been avoided by a human translator. Knowledge of the subjunctive mood is virtually non-existent.[citation needed] Moreover, the formal second person (vous) is often chosen, whatever the context or accepted usage.[citation needed] Since its English reference material contains only "you" forms, it has difficulty translating a language with "you all" or formal "you" variations.

Due to differences between languages in investment, research, and the extent of digital resources, the accuracy of Google Translate varies greatly among languages.[12] Some languages produce better results than others. Most languages from Africa, Asia, and the Pacific, tend to score poorly in relation to the scores of many well-financed European languages, Afrikaans and Chinese being the high-scoring exceptions from their continents.[8][114] No languages indigenous to Australia are included within Google Translate. Higher scores for European can be partially attributed to the Europarl Corpus, a trove of documents from the European Parliament that have been professionally translated by the mandate of the European Union into as many as 21 languages. A 2010 analysis indicated that French to English translation is relatively accurate,[115] and 2011 and 2012 analyses showed that Italian to English translation is relatively accurate as well.[116][117] 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 cannot edit sentences as a whole. Instead, one must edit sometimes arbitrary sets of characters, leading to incorrect edits.[115] A good example is Russian-to-English. Formerly one would use Google Translate to make a draft and then use a dictionary and common sense to correct the numerous mistakes. As of early 2018 Translate is sufficiently accurate to make the Russian Wikipedia accessible to those who can read English. The quality of Translate can be checked by adding it as an extension to Chrome or Firefox and applying it to the left language links of any Wikipedia article. It can be used as a dictionary by typing in words. One can translate from a book by using a scanner and an OCR like Google Drive, but this takes about five minutes per page.

In its Written Words Translation function, there is a word limit on the amount of text that can be translated at once.[17] Therefore, long text should be transferred to a document form and translated through its Document Translate function.[17]

Moreover, like all machine translation programs, Google Translate struggles with polysemy (the multiple meanings a word may have)[118][12] and multiword expressions (terms that have meanings that cannot be understood or translated by analyzing the individual word units that compose them).[119] A word in a foreign language might have two different meanings in the translated language. This might lead to mistranslations.

Additionally, grammatical errors remain a major limitation to the accuracy of Google Translate.[120]

Open-source licenses and components

Language WordNet License
Albanian Albanet CC BY 3.0/GPL 3
Arabic Arabic WordNet CC BY-SA 3.0
Catalan Multilingual Central Repository CC BY 3.0
Chinese Chinese Wordnet Wordnet
Danish DanNet Wordnet
English Princeton WordNet Wordnet
Finnish FinnWordNet Wordnet
French WOLF (WOrdnet Libre du Français) CeCILL-C
Galician Multilingual Central Repository CC BY 3.0
Haitian Creole MIT-Haiti Initiative CC BY 4.0
Hebrew Hebrew Wordnet Wordnet
Indonesian Wordnet Bahasa MIT
Italian MultiWordNet CC BY 3.0
Japanese Japanese Wordnet Wordnet
Malay Wordnet Bahasa MIT
Norwegian Norwegian Wordnet Wordnet
Persian Persian Wordnet Free-to-use
Polish plWordNet Wordnet
Portuguese OpenWN-PT CC BY-SA 3.0
Spanish Multilingual Central Repository CC BY 3.0
Thai Thai Wordnet Wordnet

Irish language data from Foras na Gaeilge's New English-Irish Dictionary (English database designed and developed for Foras na Gaeilge by Lexicography MasterClass Ltd.)

Welsh language data from Gweiadur by Gwerin.

Certain content is copyright Oxford University Press USA. Some phrase translations come from Wikitravel.[121]

Reviews

Shortly after launching the translation service for the first time, Google won an international competition for English–Arabic and English–Chinese machine translation.[122]

Translation mistakes and oddities

Since Google Translate used statistical matching to translate, translated text can often include apparently nonsensical and obvious errors,[123] often swapping common terms for similar but nonequivalent common terms in the other language,[124] as well as inverting sentence meaning.[125] Novelty websites like Bad Translator and Translation Party have utilized the service to produce humorous text by translating back and forth between multiple languages,[126] similar to the children's game telephone.[127]

See also


References

  1. "Translations Made Simple: The Usefulness of Translation Apps". April 8, 2020. https://www.ulatus.com/translation-blog/most-globally-used-translated-apps/. 
  2. 2.00 2.01 2.02 2.03 2.04 2.05 2.06 2.07 2.08 2.09 2.10 2.11 2.12 2.13 2.14 2.15 2.16 2.17 2.18 2.19 2.20 2.21 2.22 2.23 Caswell, Isaac (2022-12-05). "Google Translate Learns 24 New Languages" (in en). https://blog.google/products/translate/24-new-languages/. 
  3. Turovsky, Barak (April 28, 2016). "Ten years of Google Translate". Google Inc.. https://www.blog.google/products/translate/ten-years-of-google-translate/. 
  4. Shankland, Stephen (May 18, 2013). "Google Translate now serves 200 million people daily". Red Ventures; CBS Interactive (at the time of publication). https://www.cnet.com/news/google-translate-now-serves-200-million-people-daily/. 
  5. 5.0 5.1 Benjamin, Martin (April 1, 2019). "How GT Pivots through English". https://www.teachyoubackwards.com/extras/pivot/. 
  6. Benjamin, Martin (April 1, 2019). "Catalan to Spanish Translations". https://www.teachyoubackwards.com/extras/catalan-to-spanish-translations/. 
  7. Hofstadter, Douglas (January 30, 2018). "The Shallowness of Google Translate". Emerson Collective. https://www.theatlantic.com/technology/archive/2018/01/the-shallowness-of-google-translate/551570/. 
  8. 8.0 8.1 8.2 8.3 Benjamin, Martin (March 30, 2019). "Source data for Teach You Backwards: An In-Depth Study of Google Translate for 108 Languages". https://docs.google.com/spreadsheets/d/1fJQLMj8O5z3Q7eKDxi1tNNrFipiEL0UDyaEF0fleZ54/edit?pli=1#gid=0. 
  9. 9.0 9.1 9.2 9.3 9.4 9.5 Cite error: Invalid <ref> tag; no text was provided for refs named Turovsky, Barak, found in translation
  10. 10.0 10.1 10.2 10.3 10.4 10.5 Sommerlad, Joe (June 19, 2018). "Google Translate: How does the search giant's multilingual interpreter actually work?". https://www.independent.co.uk/life-style/gadgets-and-tech/news/google-translate-how-work-foreign-languages-interpreter-app-search-engine-a8406131.html. 
  11. 11.0 11.1 11.2 Petrovan, Bogdan (January 14, 2015). "Google Translate just got smarter: Word Lens and instant voice translations in the latest update". https://www.androidauthority.com/google-translate-word-lens-voice-translations-580312/. 
  12. 12.0 12.1 12.2 12.3 12.4 McGuire, Nick; Argondizzo, Peter (July 26, 2018). "How accurate is Google Translate in 2018?". https://www.argotrans.com/blog/accurate-google-translate-2018/. 
  13. Wiggers, Kyle (September 30, 2022). "Google appears to have disabled Google Translate in parts of China". AOL. https://techcrunch.com/2022/09/30/google-appears-to-have-disabled-google-translate-in-parts-of-china/. 
  14. Strumpf, Dan (October 3, 2022). "Google Pulls Translation App From China". The Wall Street Journal. Dow Jones & Company. https://www.wsj.com/articles/google-pulls-translation-app-from-china-11664795087. 
  15. 15.0 15.1 15.2 "Google Translate - A Personal Interpreter on Your Phone or Computer". Google Inc.. https://translate.google.com/intl/en/about/. 
  16. 16.0 16.1 16.2 "Google Translate Help". Google Inc.. https://support.google.com/translate/?hl=en. 
  17. 17.0 17.1 17.2 17.3 "Translate written words". Google Inc.. https://support.google.com/translate/answer/6142478/?hl=en. 
  18. 18.0 18.1 18.2 "Translate documents & webpages". Google Inc.. https://support.google.com/translate/answer/2534559/?hl=en. 
  19. 19.0 19.1 "Translate by speech". Google Inc.. https://support.google.com/translate/answer/6142468/?hl=en. 
  20. "Translate text in other apps". Google Inc.. https://support.google.com/translate/answer/6350658/?hl=en. 
  21. "Translate images". Google Inc.. https://support.google.com/translate/answer/6142483/?hl=en. 
  22. 22.0 22.1 "Translate with handwriting or virtual keyboard". Google Inc.. https://support.google.com/translate/answer/6142469/?hl=en. 
  23. "Translate a bilingual conversation". Google Inc.. https://support.google.com/translate/answer/6142474/?hl=en. 
  24. "Transcribe in Google Translate". Google Inc.. https://support.google.com/translate/answer/9724492/?hl=en. 
  25. Benjamin, Martin (March 30, 2019). "Dictionary - When & How to Use Google Translate". https://www.teachyoubackwards.com/how-to-use-google-translate/#dictionary. 
  26. 26.0 26.1 Benjamin, Martin (April 1, 2019). "Ooga Booga: Better than a Dictionary - Qualitative Analysis of Google Translate across 108 Languages". https://www.teachyoubackwards.com/qualitative-analysis/#ooga-booga. 
  27. "Save translations in a phrasebook". Google Inc.. https://support.google.com/translate/answer/6142480/?hl=en. 
  28. AK, Sony (December 5, 2019). "Practical Puppeteer: Playing with Google Translate to translate a text". https://dev.to/sonyarianto/practical-puppeteer-access-to-google-translate-to-translate-a-text-160j. 
  29. "Search results for "Google Translate"". Add-ons for Firefox. Mozilla Foundation. https://addons.mozilla.org/en/firefox/search/?q=Google+Translate. 
  30. "Google Translate". Chrome Web Store. Google Inc.. https://chrome.google.com/webstore/detail/google-translate/aapbdbdomjkkjkaonfhkkikfgjllcleb/?hl=en. 
  31. Baldwin, Roberto (October 16, 2014). "Google introduces Google Translate Chrome Extension for inline translations of text". Financial Times. https://thenextweb.com/news/google-introduces-google-translate-chrome-extension-inline-translations-text. 
  32. Brinkmann, Martin (July 19, 2016). "Google Translate Integrated In Google Chrome 5". Ghacks Technology News (Ghacks). https://www.ghacks.net/2010/02/07/google-translate-integrated-in-google-chrome-5/. 
  33. "Google Chrome 5 features an integrated Google Translate service". February 15, 2010. https://stuff.techwhack.com/8388-google-chrome-5-translate. 
  34. Wauters, Robin (February 14, 2010). "Rant: Google Translate Toolbar In Chrome 5 Needs An 'Off' Button". AOL. https://techcrunch.com/2010/02/14/google-chrome-5-translate-toolbar/. 
  35. "Google Translate APKs". https://www.apkmirror.com/apk/google-inc/translate/. 
  36. "Google Translate". https://apps.apple.com/app/id414706506. 
  37. 37.0 37.1 Turovsky, Barak (July 29, 2015). "See the world in your language with Google Translate". Google Inc.. https://blog.google/products/translate/see-world-in-your-language-with-google/. 
  38. 38.0 38.1 Setalvad, Ariha (July 29, 2015). "Google Translate adds 20 new languages to video text translation". Vox Media. https://www.theverge.com/2015/7/29/9061135/google-translate-update-new-languages-word-lens. 
  39. Zhu, Wenzhang (February 8, 2011). "Introducing the Google Translate app for iPhone". Google Inc.. https://googlemobile.blogspot.com/2011/02/introducing-google-translate-app-for.html. 
  40. Hutchison, Allen (August 7, 2008). "Google Translate now for iPhone". Google Inc.. https://googlemobile.blogspot.com/2008/08/google-translate-now-for-iphone.html. 
  41. "Google Translate on the App Store". Google. https://apps.apple.com/app/google-translate/id414706506. 
  42. Hachman, Mark (January 12, 2011). "Google Translate's New 'Conversation Mode': Hands On". Ziff Davis. https://www.pcmag.com/article2/0,2817,2375655,00.asp. 
  43. Kim, Ryan (October 13, 2011). "Google Translate conversation mode expands to 14 languages". Gigaom. https://gigaom.com/2011/10/13/google-translate-conversation-mode-adds-14-languages/. 
  44. Velazco, Chris (October 13, 2011). "Google Translate For Android Gets Upgraded "Conversation Mode"". AOL. https://techcrunch.com/2011/10/13/google-translate-for-android-gets-upgraded-conversation-mode/. 
  45. Turovsky, Barak (January 14, 2015). "Hallo, hola, olá to the new, more powerful Google Translate app". Google Inc.. https://blog.google/products/translate/hallo-hola-ola-more-powerful-translate/. 
  46. Russell, Jon (January 14, 2015). "Google Translate Now Does Real-Time Voice And Sign Translations On Mobile". AOL. https://techcrunch.com/2015/01/14/amaaaaaazing/. 
  47. Good, Otávio (July 29, 2015). "How Google Translate squeezes deep learning onto a phone". Google Inc.. https://ai.googleblog.com/2015/07/how-google-translate-squeezes-deep.html. 
  48. Gush, Andrew (July 29, 2015). "Google Translate adds video translation support for 25 more languages". https://www.androidauthority.com/google-translate-video-translation-629893/. 
  49. Olanoff, Drew (July 29, 2015). "Google Translate's App Now Instantly Translates Printed Text In 27 Languages". AOL. https://techcrunch.com/2015/07/29/google-translates-app-now-instantly-translates-printed-text-in-27-languages/. 
  50. Benjamin, Martin (March 30, 2019). "Instant Camera Translation - Introduction: Into the Black Box of Google Translate". https://www.teachyoubackwards.com/introduction/#instant-camera. 
  51. Kastrenakes, Jacob (May 11, 2016). "Google Translate now works inside any app on Android". Vox Media. https://www.theverge.com/2016/5/11/11656900/tap-to-translate-google-translate-inside-any-android-app. 
  52. 52.0 52.1 Feldman, Adam (June 3, 2011). "Spring cleaning for some of our APIs (Google Code Blog)". in Knaster, Scott. Official Google Code Blog. Google Inc.. https://googlecode.blogspot.com/2011/05/spring-cleaning-for-some-of-our-apis.html. 
  53. 53.0 53.1 Feldman, Adam (June 3, 2011). "Spring cleaning for some of our APIs (Google Developers Blog)". in Knaster, Scott. Google Developers Blog. Google Inc.. https://developers.googleblog.com/2011/06/spring-cleaning-for-some-of-our-apis.html. 
  54. Grunwald, Dave (May 27, 2011). "BREAKING NEWS! Google to shut down Translate API". https://blog.gts-translation.com/2011/05/27/breaking-news-google-to-shut-down-translate-api/. 
  55. "Google Translate API (deprecated)". Google Code. Google Inc.. https://code.google.com/apis/language/translate/overview.html. 
  56. Grunwald, Dave (June 4, 2011). "Google cancels plan to shutdown Translate API. To start charging for translations". https://blog.gts-translation.com/2011/06/04/google-cancels-plan-to-shutdown-translate-api-to-start-charging-for-translations/. 
  57. Wong, George (May 27, 2011). "Google gets rid of APIs for Translate and other services". https://www.ubergizmo.com/2011/05/google-rid-translate-api/. 
  58. Burnette, Ed (May 27, 2011). "Google pulls the rug out from under web service API developers, nixes Google Translate and 17 others". ZDNet. https://www.zdnet.com/article/google-pulls-the-rug-out-from-under-web-service-api-developers-nixes-google-translate-and-17-others/. 
  59. "See which features work with each language". Google Inc.. https://translate.google.com/intl/en/about/languages/. 
  60. 60.00 60.01 60.02 60.03 60.04 60.05 60.06 60.07 60.08 60.09 60.10 60.11 60.12 Kelman, Sveta (2016-02-17). "From Amharic to Xhosa, Introducing Translate in 13 New Languages — Now Over 100 in Total!" (in en). https://blog.google/products/translate/from-amharic-to-xhosa-introducing/. 
  61. 61.0 61.1 61.2 61.3 61.4 Venugopal, Ashish (2010-05-13). "Five More Languages on translate.google.com" (in en). https://translate.googleblog.com/2010/05/five-more-languages-on.html. 
  62. 62.0 62.1 62.2 62.3 62.4 Kelman, Sveta (2013-05-08). "More than 70 of the World's Languages in the Blink of an Eye" (in en). https://blog.google/products/translate/more-than-70-of-worlds-languages-in/. 
  63. 63.0 63.1 63.2 63.3 63.4 63.5 63.6 63.7 63.8 63.9 "Google Translate – 10 More Languages with Your Help" (in en). 2014-12-11. https://translate.googleblog.com/2014/12/google-translate-10-more-languages-with.html. 
  64. Brants, Thorsten (2012-02-22). "Tutmonda helplingvo por ĉiuj homoj" (in en). https://translate.googleblog.com/2012/02/tutmonda-helplingvo-por-ciuj-homoj.html. 
  65. 65.0 65.1 65.2 65.3 65.4 65.5 65.6 65.7 65.8 Mauser, Arne (2013-12-10). "Google Translate – Now in 80 Languages" (in en). https://translate.googleblog.com/2013/12/google-translate-now-in-80-languages.html. 
  66. Mauser, Arne (2013-04-18). "Google Translate Now Supports Khmer" (in en). https://translate.googleblog.com/2013/04/google-translate-now-supports-khmer.html. 
  67. 67.0 67.1 67.2 67.3 67.4 Caswell, Isaac (2020-02-26). "Google Translate Adds Five Languages" (in en). https://blog.google/products/translate/five-new-languages/. 
  68. Brants, Thorsten (2012-09-13). "Translating Lao" (in en). https://translate.googleblog.com/2012/09/translating-lao_13.html. 
  69. "Google Translate - Contribute". Google Inc.. https://translate.google.com/contribute?hl=en. 
  70. Chidley-Hill, John (February 21, 2021). "Online petition asks for Cree language to be added to Google Translate". CTV News, Bell Media (owner). https://www.ctvnews.ca/sci-tech/online-petition-asks-for-cree-language-to-be-added-to-google-translate-1.5317866. 
  71. Beattie, Samantha (February 23, 2021). "Google Translate's Exclusion Of Indigenous Languages A 'Squandered' Opportunity". BuzzFeed. https://www.huffpost.com/archive/ca/entry/google-translate-cree-indigenous-language_ca_6035242ac5b67c329620c3e3. 
  72. Cite error: Invalid <ref> tag; no text was provided for refs named Statistical machine translation
  73. 73.0 73.1 Och, Franz Josef (September 12, 2005). "Statistical Machine Translation: Foundations and Recent Advances". Phuket, Thailand: Asia-Pacific Association for Machine Translation. https://www.mt-archive.info/MTS-2005-Och.pdf. 
  74. MT Summit X: The Tenth Machine Translation Summit (proceedings). Phuket, Thailand: Asia-Pacific Association for Machine Translation. September 12–16, 2005. ISBN 9789747431261. https://books.google.com/books?id=oooQAAAACAAJ. Retrieved February 4, 2022. 
  75. "Franz Och, Ph.D., Expert in Machine Learning and Machine Translation, Joins Human Longevity, Inc. as Chief Data Scientist" (Press release). La Jolla, California: Human Longevity, Inc. July 29, 2014. Archived from the original on August 7, 2020. Retrieved January 15, 2015.
  76. French to Russian translation translates the untranslated non-French word "obvious" from pivot (intermediate) English to Russian le mot 'obvious' n'est pas français"очевидными" слово не французское
  77. We pretend that this English article is German when asking Google to translate it to French. Google, because it does not find the English words in the German dictionary, leaves those words unchanged as one can show it with this spelllling misssstake. But it translates them to French nonetheless. That's because Google translates German → English → French and that the unchanged English words undergo the second translation. The word "außergewöhnlich" however will be translated twice.
  78. 78.0 78.1 Boitet, Christian; Blanchon, Hervé; Seligman, Mark; Bellynck, Valérie (January 31, 2011). "MT on and for the Web". https://www-clips.imag.fr/geta/herve.blanchon/Pdfs/NLP-KE-10.pdf. 
  79. 79.0 79.1 P.Y. (October 25, 2010). "Wrong translation to Ukrainian language". https://groups.google.com/group/google-translate-general/msg/bde8be4a58eb74c0. 
  80. Google Translation mixes up "tu" and plural or polite "vous" Je vous aime. Tu es ici. You are here. → Я люблю тебя. Вы здесь. Вы здесь.
  81. Adams, Tim (December 19, 2010). "Can Google break the computer language barrier?". https://www.theguardian.com/technology/2010/dec/19/google-translate-computers-languages. 
  82. Tanner, Adam (March 28, 2007). "Google seeks world of instant translations". Thomson Reuters. https://www.reuters.com/article/us-google-translate-idUSN1921881520070328. 
  83. 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.
  84. "Inside Google Translate (old)". Google Inc.. https://translate.google.com/about/intl/en_ALL. 
  85. Chitu, Alex (October 22, 2007). "Google Switches to Its Own Translation System". Google Inc.. https://googlesystem.blogspot.com/2007/10/google-translate-switches-to-googles.html. 
  86. Schwartz, Barry (October 23, 2007). "Google Translate Drops Systran For Home Brewed Translation". https://searchengineland.com/google-translate-drops-systran-for-home-brewed-translation-12502. 
  87. Southern, Matt (July 28, 2014). "Google Seeks Community Help To Improve Google Translate". https://www.searchenginejournal.com/google-seeks-community-help-improve-google-translate/112741/. 
  88. Kelman, Sveta (July 25, 2014). "Translate Community: Help us improve Google Translate!". Google Inc.. https://translate.googleblog.com/2014/07/translate-community-help-us-improve.html. 
  89. 89.0 89.1 89.2 "Help Us Improve the Google Translate Tool". Google Inc.. https://translate.google.com/intl/en/about/contribute/. 
  90. Lardinois, Frederic (July 25, 2014). "Google Wants To Improve Its Translations Through Crowdsourcing". AOL. https://techcrunch.com/2014/07/25/google-wants-to-improve-its-translations-through-crowdsourcing/. 
  91. Summers, Nick (July 25, 2014). "Google sets up a community site to help improve Google Translate". Financial Times. https://thenextweb.com/news/google-sets-community-site-help-improve-google-translate. 
  92. "Google Translate Community FAQ". https://docs.google.com/document/d/1dwS4CZzgZwmvoB9pAx4A6Yytmv7itk_XE968RMiqpMY/pub. 
  93. Whitwam, Ryan (August 29, 2016). "New Google Crowdsource app asks you to help with translation and text transcription a few seconds at a time". https://www.androidpolice.com/2016/08/29/new-google-crowdsource-app-asks-help-translation-text-transcription-seconds-time/. 
  94. Shankland, Stephen (August 29, 2016). "New Crowdsource app lets you work for Google for free". Red Ventures; CBS Interactive (at the time of publication). https://www.cnet.com/news/new-crowdsource-app-lets-you-work-for-google-for-free/. 
  95. Benjamin, Martin (April 1, 2019). "Myth 5: Google Translate learns from its users - Qualitative Analysis of Google Translate across 108 Languages". https://www.teachyoubackwards.com/qualitative-analysis/#myth-5. 
  96. Lange, William (February 7, 2017). "Statistical Vs Neural Machine Translation". United Language Group. https://daily.unitedlanguagegroup.com/stories/editorials/statistical-vs-neural-machine-translation. 
  97. "Statistical Vs. Neural Machine Translation". United Language Group. https://unitedlanguagegroup.com/blog/statistical-vs-neural-machine-translation/. 
  98. 98.0 98.1 Le, Quoc V.; Schuster, Mike (September 27, 2016). "A Neural Network for Machine Translation, at Production Scale". Google AI Blog. Google Inc.. https://ai.googleblog.com/2016/09/a-neural-network-for-machine.html. 
  99. 99.0 99.1 99.2 99.3 Schuster, Mike; Johnson, Melvin; Thorat, Nikhil (November 22, 2016). "Zero-Shot Translation with Google's Multilingual Neural Machine Translation System". Google Inc.. https://ai.googleblog.com/2016/11/zero-shot-translation-with-googles.html. 
  100. Fewster, Gil (January 5, 2017). "The mind-blowing AI announcement from Google that you probably missed.". freeCodeCamp. https://www.freecodecamp.org/news/the-mind-blowing-ai-announcement-from-google-that-you-probably-missed-2ffd31334805/. 
  101. Hochreiter, Sepp; Schmidhuber, Jürgen (November 15, 1997). "Long short-term memory". Neural Computation 9 (8): 1735–1780. doi:10.1162/neco.1997.9.8.1735. PMID 9377276. https://www.researchgate.net/publication/13853244. Retrieved May 14, 2017. 
  102. Gers, Felix A.; Schmidhuber, Jürgen; Cummins, Fred (October 1, 2000). "Learning to Forget: Continual Prediction with LSTM". Neural Computation 12 (10): 2451–2471. doi:10.1162/089976600300015015. PMID 11032042. https://www.researchgate.net/publication/12292425. Retrieved May 14, 2017. 
  103. Cite error: Invalid <ref> tag; no text was provided for refs named bridging the gap
  104. Cade, Metz (September 27, 2016). "An Infusion of AI Makes Google Translate More Powerful Than Ever". Wired. https://www.wired.com/2016/09/google-claims-ai-breakthrough-machine-translation/. Retrieved May 14, 2017. 
  105. McDonald, Chris (January 7, 2017). "Ok slow down". https://medium.com/@chrismcdonald_94568/ok-slow-down-516f93f83ac8. 
  106. Davenport, Corbin (March 6, 2017). "Google Translate now uses neural machine translation for some languages". https://www.androidpolice.com/2017/03/06/google-translate-now-uses-neural-machine-translation-languages/. 
  107. Hager, Ryne (April 25, 2017). "Google adds Indonesian and eight new Indian languages to its neural machine translation". https://www.androidpolice.com/2017/04/25/google-adds-indonesian-eight-new-indian-languages-neural-machine-translation/. 
  108. Benjamin, Martin (March 30, 2019). "The 5 conditions for satisfactory approximations with Google Translate - Conclusions: Real Data, Fake Data & Google Translate". https://www.teachyoubackwards.com/conclusions/#conditions. 
  109. Benjamin, Martin (March 30, 2019). "Empirical Evaluation of Google Translate across 107 Languages". https://www.teachyoubackwards.com/empirical-evaluation/. 
  110. Benjamin, Martin (March 30, 2019). "Non-English Pairs - Empirical Evaluation of Google Translate across 107 Languages". https://www.teachyoubackwards.com/empirical-evaluation/#non-english. 
  111. Aiken, Milam; Balan, Shilpa (April 2011). "An Analysis of Google Translate Accuracy". Translation Journal 16 (2). https://translationjournal.net/journal/56google.htm. Retrieved November 29, 2018. 
  112. 112.0 112.1 Li, Haiying; Graesser, Arthur; Cai, Zhiqiang (May 3, 2014). "Comparison of Google Translation with Human Translation". Proceedings of the Twenty-Seventh International Florida Artificial Intelligence Research Society Conference (FLAIRS Conference). https://pdfs.semanticscholar.org/1187/d4bc0c83804c15cd6cc1b43670d27f5fe9b6.pdf. Retrieved November 29, 2018. 
  113. Benjamin, Martin (April 1, 2019). "Polysemy in top 100 Oxford English Corpus words within Wiktionary". https://docs.google.com/spreadsheets/d/1bHK7BE2kMDh57Ttt0qfQwGrfACrCzG-91BgdLPoc-5o/edit#gid=0. 
  114. Freitas, Connor; Liu, Yudong (December 15, 2017). "Exploring the Differences between Human and Machine Translation". Western Washington University: 5. https://cedar.wwu.edu/cgi/viewcontent.cgi?article=1060&context=wwu_honors. Retrieved December 5, 2018. 
  115. 115.0 115.1 Shen, Ethan (June 2010). "Comparison of online machine translation tools". https://www.tcworld.info/e-magazine/translation-and-localization/comparison-of-online-machine-translation-tools-34/. 
  116. Pecoraro, Christopher (August 17, 2011). "Microsoft Bing Translator and Google Translate Compared". https://www.chrispecoraro.com/microsoft-bing-translator-and-google-translate-compared/index.html. 
  117. Pecoraro, Christopher (January 30, 2012). "Microsoft Bing Translator and Google Translate compared (update)". https://www.chrispecoraro.com/microsoft-bing-translator-and-google-translate-compared-2/index.html. 
  118. Benjamin, Martin (April 1, 2019). "Polysemy – words with multiple meanings - The Astounding Mathematics of Machine Translation". https://www.teachyoubackwards.com/mt-mathematics/#polysemy. 
  119. Benjamin, Martin (April 1, 2019). "Party terms (or multiword expressions) – words that play together - The Astounding Mathematics of Machine Translation". https://www.teachyoubackwards.com/mt-mathematics/#party-terms. 
  120. Template:Cite SSRN International Journal of Linguistics, Literature and Translation (IJLLT) 2(3):196-200, 2019. Retrieved August 26, 2020
  121. "Open source components and licenses.". Google Inc.. https://translate.google.com/intl/en/about/license/. 
  122. Nielsen, Michael A. (October 3, 2011). Reinventing discovery: the new era of networked science. Princeton, NJ: Princeton University Press. p. 125. ISBN 978-0-691-14890-8. https://books.google.com/books?id=afqfFW8WV9cC. Retrieved February 24, 2012. 
  123. Gomes, Lee (July 22, 2010). "Google Translate Tangles With Computer Learning". https://www.forbes.com/forbes/2010/0809/technology-computer-learning-google-translate.html. 
  124. Weinberg, Nathan (September 10, 2007). "Google Translates Ivan the Terrible as "Abraham Lincoln"". https://google.blognewschannel.com/archives/2007/09/10/google-translates-ivan-the-terrible-as-abraham-lincoln/. 
  125. Twisted Translations (February 10, 2015). "Google Translate Sings: "Bohemian Rhapsody" by Queen". Google Inc.. https://www.youtube.com/watch?v=rwOH3YsraNs. 
  126. Topolyanskaya, Alyona (January 28, 2010). "Google Lost in Translation". https://www.mn.ru/news/20100128/55406807.html. 
  127. Kincaid, Jason (August 7, 2009). "Translation Party: Tapping Into Google Translate's Untold Creative Genius". AOL. https://techcrunch.com/2009/08/07/translation-party-tapping-into-google-translates-untold-creative-genius/. 

External links