Google Translate

History

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

Originally, Google Translate was released as a statistical machine translation (SMT) service. The input text had to be translated into English first before being translated into the selected language. 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.

In January 2010, Google introduced an Android app and iOS version in February 2011 to serve as a portable personal interpreter. 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.

In May 2014, Google acquired Word Lens to improve the quality of visual and voice translation. 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.

In November 2016, Google transitioned its translating method to a system called neural machine translation. 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 arXiv|last1=Wu|first1=Yonghui|last2=Schuster

In 2017, Google Translate was used during a court hearing when court officials at Teesside Magistrates' Court failed to book an interpreter for the Chinese defendant.

A petition for Google to add Cree to Google Translate was created in 2021, but it was not one of the languages in development at the time of the Translate Community's closure.

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

In 2024, a record of 110 languages including Cantonese, Tok Pisin and some regional languages in Russia including Bashkir, Chechen, Ossetian and Crimean Tatar were added. The languages were added through the help of the PaLM 2 Generative AI model.

Functions

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

• Written Words Translation: a function that translates written words or text to a foreign language.
• Website Translation: a function that translates a whole webpage to selected languages.
• 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.
• Speech Translation: a function that instantly translates spoken language into the selected foreign language.
• 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.
• Image Translation: a function that identifies text in a picture taken by the users and translates text on the screen instantly by images.
• 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.
• Bilingual Conversation Translation: a function that translates conversations in multiple languages.
• Transcription: a function that transcribes speech in different languages.

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.

Features

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. For some languages, Google Translate can synthesize speech from text, 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 and has been shown to invent translations in all languages for words it does not recognize. 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. Users can save translation proposals in a "phrasebook" for later use, and a shareable URL is generated for each translation. For some languages, text can be entered via an on-screen keyboard, whether through handwriting recognition or speech recognition. 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 automatically transliterated from their 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.

]] 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 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 (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 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. In February 2010, Google Translate was integrated into the Google Chrome browser by default, for optional automatic webpage translation.

Mobile app

(for iOS) 177.4 MB (iOS) The Google Translate app for Android and iOS supports 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".

The Android app was released in January 2010, and for iOS on February 8, 2011, after an HTML5 web application was released for iOS users in August 2008. 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+.

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. Originally limited to English and Spanish, the feature received support for 12 new languages, still in testing, the following October.

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. 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). 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.

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.

API

On May 26, 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 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

the following 249 languages, dialects and language varieties written in different scripts ( unique languages and dialects) are supported by Google Translate.

1. Abkhaz
2. Acehnese
3. Acholi
4. Afar
5. Afrikaans
6. Albanian
7. Alur
8. Amharic
9. Arabic
10. Armenian
11. Assamese
12. Avar
13. Awadhi
14. Aymara
15. Azerbaijani
16. Balinese
17. Baluchi
18. Bambara
19. Baoulé
20. Bashkir
21. Basque
22. Batak Karo
23. Batak Simalungun
24. Batak Toba
25. Belarusian
26. Bemba
27. Bengali
28. Betawi
29. Bhojpuri
30. Bikol
31. Bosnian
32. Breton
33. Bulgarian
34. Buryat
35. Cantonese
36. Catalan
37. Cebuano
38. Chamorro
39. Chechen
40. Chichewa
41. Chinese (Simplified)
42. Chinese (Traditional)
43. Chuukese
44. Chuvash
45. Corsican
46. Crimean Tatar (Cyrillic)
47. Crimean Tatar (Latin)
48. Croatian
49. Czech
50. Danish
51. Dari
52. Dhivehi
53. Dinka
54. Dogri
55. Dombe
56. Dutch
57. Dyula
58. Dzongkha
59. English
60. Esperanto
61. Estonian
62. Ewe
63. Faroese
64. Fijian
65. Filipino
66. Finnish
67. Fon
68. French
69. French (Canada)
70. Frisian
71. Friulian
72. Fulani
73. Ga
74. Galician
75. Georgian
76. German
77. Greek
78. Guarani
79. Gujarati
80. Haitian Creole
81. Hakha Chin
82. Hausa
83. Hawaiian
84. Hebrew
85. Hiligaynon
86. Hindi
87. Hmong
88. Hungarian
89. Hunsrik
90. Iban
91. Icelandic
92. Igbo
93. Ilocano
94. Indonesian
95. Inuktut (Latin)
96. Inuktut (Syllabics)
97. Irish
98. Italian
99. Jamaican Patois
100. Japanese
101. Javanese
102. Jingpo
103. Kalaallisut
104. Kannada
105. Kanuri
106. Kapampangan
107. Kazakh
108. Khasi
109. Khmer
110. Kiga
111. Kikongo
112. Kinyarwanda
113. Kituba
114. Kokborok
115. Komi
116. Konkani
117. Korean
118. Krio
119. Kurdish (Kurmanji)
120. Kurdish (Sorani)
121. Kyrgyz
122. Lao
123. Latgalian
124. Latin
125. Latvian
126. Ligurian
127. Limburgish
128. Lingala
129. Lithuanian
130. Lombard
131. Luganda
132. Luo
133. Luxembourgish
134. Macedonian
135. Madurese
136. Maithili
137. Makassar
138. Malagasy
139. Malay
140. Malay (Jawi)
141. Malayalam
142. Maltese
143. Mam
144. Manx
145. Maori
146. Marathi
147. Marshallese
148. Marwadi
149. Mauritian Creole
150. Meadow Mari
151. Meiteilon (Manipuri)
152. Minang
153. Mizo
154. Mongolian
155. Myanmar (Burmese)
156. Nahuatl (Eastern Huasteca)
157. Ndau
158. Ndebele (South)
159. Nepalbhasa (Newari)
160. Nepali
161. NKo
162. Norwegian (Bokmål)
163. Nuer
164. Occitan
165. Odia (Oriya)
166. Oromo
167. Ossetian
168. Pangasinan
169. Papiamento
170. Pashto
171. Persian
172. Polish
173. Portuguese (Brazil)
174. Portuguese (Portugal)
175. Punjabi (Gurmukhi)
176. Punjabi (Shahmukhi)
177. Quechua
178. Qʼeqchiʼ
179. Romani
180. Romanian
181. Rundi
182. Russian
183. Sami (North)
184. Samoan
185. Sango
186. Sanskrit
187. Santali (Latin)
188. Santali (Ol Chiki)
189. Scots Gaelic
190. Sepedi
191. Serbian
192. Sesotho
193. Seychellois Creole
194. Shan
195. Shona
196. Sicilian
197. Silesian
198. Sindhi
199. Sinhala
200. Slovak
201. Slovenian
202. Somali
203. Spanish
204. Sundanese
205. Susu
206. Swahili
207. Swati
208. Swedish
209. Tahitian
210. Tajik
211. Tamazight
212. Tamazight (Tifinagh)
213. Tamil
214. Tatar
215. Telugu
216. Tetum
217. Thai
218. Tibetan
219. Tigrinya
220. Tiv
221. Tok Pisin
222. Tongan
223. Tshiluba
224. Tsonga
225. Tswana
226. Tulu
227. Tumbuka
228. Turkish
229. Turkmen
230. Tuvan
231. Twi
232. Udmurt
233. Ukrainian
234. Urdu
235. Uyghur
236. Uzbek
237. Venda
238. Venetian
239. Vietnamese
240. Waray
241. Welsh
242. Wolof
243. Xhosa
244. Yakut
245. Yiddish
246. Yoruba
247. Yucatec Maya
248. Zapotec
249. Zulu

Stages

(by chronological order of introduction)

1. 1st stage
2. English to and from French
3. English to and from German
4. English to and from Spanish
5. 2nd stage
6. English to and from Portuguese (Brazil)
7. 3rd stage
8. English to and from Italian
9. 4th stage
10. English to and from Chinese (Simplified)
11. English to and from Japanese
12. English to and from Korean
13. 5th stage (launched April 28, 2006)
14. English to and from Arabic
15. 6th stage (launched December 16, 2006)
16. English to and from Russian
17. 7th stage (launched February 9, 2007)
18. English to and from Chinese (Traditional)
19. Chinese ((Simplified) to and from Traditional)
20. 8th stage (all 25 language pairs use Google's machine translation system) (launched October 22, 2007)
21. English to and from Dutch
22. English to and from Greek
23. 9th stage
24. English to and from Hindi
25. 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)
26. Bulgarian
27. Croatian
28. Czech
29. Danish
30. Finnish
31. Norwegian (Bokmål)
32. Polish
33. Romanian
34. Swedish
35. 11th stage (launched September 25, 2008)
36. Catalan
37. Filipino (Tagalog)
38. Hebrew
39. Indonesian
40. Latvian
41. Lithuanian
42. Serbian
43. Slovak
44. Slovene
45. Ukrainian
46. Vietnamese
47. 12th stage (launched January 30, 2009)
48. Albanian
49. Estonian
50. Galician
51. Hungarian
52. Maltese
53. Thai
54. Turkish
55. 13th stage (launched June 19, 2009)
56. Persian
57. 14th stage (launched August 24, 2009)
58. Afrikaans
59. Belarusian
60. Icelandic
61. Irish
62. Macedonian
63. Malay
64. Swahili
65. Welsh
66. Yiddish
67. 15th stage (launched November 19, 2009)
68. The Beta stage is finished. Users can now choose to have the romanization written for Belarusian, Bulgarian, Chinese, Greek, Hindi, Japanese, Korean, Russian, Thai and Ukrainian. For translations from Arabic, Hindi and Persian, 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, French, German and Italian.
69. 16th stage (launched January 30, 2010)
70. Haitian Creole
71. 17th stage (launched April 2010)
72. Speech program launched in Hindi and Spanish.
73. 18th stage (launched May 5, 2010)
74. 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).
75. 19th stage (launched May 13, 2010)
76. Armenian
77. Azerbaijani
78. Basque
79. Georgian
80. Urdu
81. 20th stage (launched June 2010)
82. Provides romanization for Arabic.
83. 21st stage (launched September 2010)
84. Allows phonetic typing for Arabic, Greek, Hindi, Persian, Russian, Serbian and Urdu.
85. Latin
86. 22nd stage (launched December 2010)
87. Romanization of Arabic removed.
88. Spell check added.
89. 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 and Turkish), and also the old versions of French, German, Italian and Spanish; Latin uses the same synthesizer as Italian.
90. Speech program launched in Arabic, Japanese and Korean.
91. 23rd stage (launched January 2011)
92. Choice of different translations for a word.
93. 24th stage (launched June 2011)

• 5 new Indic languages (in alpha) and a transliterated input method:

1. Bengali
2. Gujarati
3. Kannada
4. Tamil
5. Telugu
6. 25th stage (launched July 2011)
7. Translation rating introduced.
8. 26th stage (launched January 2012)
9. Dutch male voice synthesizer replaced with female.
10. Elena by SVOX replaced the Slovak eSpeak voice.
11. Transliteration of Yiddish added.
12. 27th stage (launched February 2012)
13. Speech program launched in Thai.
14. Esperanto
15. 28th stage (launched September 2012)
16. Lao
17. 29th stage (launched October 2012)
18. Transliteration of Lao added. (alpha status)
19. 30th stage (launched October 2012)
20. New speech program launched in English.
21. 31st stage (launched November 2012)
22. New speech program in French, German, Italian, Latin and Spanish.
23. 32nd stage (launched March 2013)
24. Phrasebook added.
25. 33rd stage (launched April 2013)
26. Khmer
27. 34th stage (launched May 2013)
28. Bosnian
29. Cebuano
30. Hmong
31. Javanese
32. Marathi
33. 35th stage (launched May 2013)
34. 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.
35. 36th stage (launched December 2013)
36. Hausa
37. Igbo
38. Maori
39. Mongolian
40. Nepali
41. Punjabi (Gurmukhi)
42. Somali
43. Yoruba
44. Zulu
45. 37th stage (launched June 2014)
46. Definition of words added.
47. 38th stage (launched December 2014)
48. Burmese
49. Chewa
50. Kazakh
51. Malagasy
52. Malayalam
53. Sinhala
54. Sotho
55. Sundanese
56. Tajik
57. Uzbek
58. 39th stage (launched October 2015)
59. Transliteration of Arabic restored.
60. 40th stage (launched November 2015)
61. Aurebesh
62. 41st stage (launched February 2016)
63. Aurebesh removed.
64. Speech program launched in Bengali.
65. Amharic
66. Corsican
67. Hawaiian
68. Kurdish (Kurmanji)
69. Kyrgyz
70. Luxembourgish
71. Pashto
72. Samoan
73. Scottish Gaelic
74. Shona
75. Sindhi
76. West Frisian
77. Xhosa
78. 42nd stage (launched September 2016)
79. Speech program launched in Ukrainian.
80. 43rd stage (launched December 2016)
81. Speech program launched in Khmer and Sinhala.
82. 44th stage (launched June 2018)
83. Speech program launched in Burmese, Malayalam, Marathi, Nepali and Telugu.
84. 45th stage (launched September 2019)
85. Speech program launched in Gujarati, Kannada and Urdu.
86. 46th stage (launched February 2020)
87. Kinyarwanda
88. Odia
89. Tatar
90. Turkmen
91. Uyghur
92. 47th stage (launched February 2021)
93. Speech program launched in Afrikaans, Bulgarian, Catalan, Icelandic, Latvian, and Serbian (changed from eSpeak to a natural voice).
94. New speech system (WaveNet) for several languages.
95. 48th stage (launched January 2022)
96. Speech program launched in Hebrew.
97. 49th stage (launched May 2022)
98. Assamese
99. Aymara
100. Bambara
101. Bhojpuri
102. Dogri
103. Ewe
104. Guarani
105. Ilocano
106. Konkani
107. Krio
108. Kurdish (Sorani)
109. Lingala
110. Luganda
111. Maithili
112. Maldivian
113. Meitei
114. Mizo
115. Northern Sotho
116. Oromo
117. Quechua
118. Sanskrit
119. Tigrinya
120. Tsonga
121. Twi
122. eSpeak voice synthesizer removed from Armenian, Esperanto, Macedonian and Welsh.
123. 50th stage (launched November 2022)
124. Speech program launched in Albanian, Bosnian and Swahili (changed from eSpeak to natural).
125. New speech program launched in Malayalam, Marathi and Tamil.
126. 51st stage (launched March 2023)
127. Speech program launched in Croatian (changed from eSpeak to natural).
128. 52nd stage (launched April 2023)
129. Speech program launched in Welsh (only on Google search results).
130. New speech programs launched in Chinese (simplified and traditional), German, Indonesian, Malay, Malayalam, Tamil, and Telugu (Chinese, German, Indonesian, Malayalam and Tamil reverted from WaveNet).
131. 53rd stage (launched June 2023)
132. Speech program launched in Lithuanian and Punjabi.
133. 54th stage (launched June 2024)
134. Abkhaz
135. Acehnese
136. Acholi
137. Afar
138. Alur
139. Avar
140. Awadhi
141. Balinese
142. Baluchi
143. Baoulé
144. Bashkir
145. Batak Karo
146. Batak Simalungun
147. Batak Toba
148. Bemba
149. Betawi
150. Bikol
151. Breton
152. Buryat
153. Cantonese
154. Chamorro
155. Chechen
156. Chuukese
157. Chuvash
158. Crimean Tatar (Cyrillic)
159. Dari
160. Dinka
161. Dombe
162. Dyula
163. Dzongkha
164. Faroese
165. Fijian
166. Fon
167. Friulian
168. Fulani
169. Ga
170. Hakha Chin
171. Hiligaynon
172. Hunsrik
173. Iban
174. Jamaican Patois
175. Jingpo
176. Kalaallisut
177. Kanuri
178. Kapampangan
179. Khasi
180. Kiga
181. Kikongo
182. Kituba
183. Kokborok
184. Komi
185. Latgalian
186. Ligurian
187. Limburgish
188. Lombard
189. Luo
190. Madurese
191. Makassar
192. Malay (Jawi)
193. Mam
194. Manx
195. Marshallese
196. Marwadi
197. Mauritian Creole
198. Meadow Mari
199. Minang
200. Nahuatl (Eastern Huasteca)
201. Ndau
202. Ndebele (South)
203. Nepalbhasa (Newari)
204. NKo
205. Nuer
206. Occitan
207. Ossetian
208. Pangasinan
209. Papiamento
210. Portuguese (Portugal)
211. Punjabi (Shahmukhi)
212. Qʼeqchiʼ
213. Romani
214. Rundi
215. Sami (North)
216. Sango
217. Santali
218. Seychellois Creole
219. Shan
220. Sicilian
221. Silesian
222. Susu
223. Swati
224. Tahitian
225. Tamazight
226. Tamazight (Tifinagh)
227. Tetum
228. Tibetan
229. Tiv
230. Tok Pisin
231. Tongan
232. Tswana
233. Tulu
234. Tumbuka
235. Tuvan
236. Udmurt
237. Venda
238. Venetian
239. Waray
240. Wolof
241. Yakut
242. Yucatec Maya
243. Zapotec
244. Speech program launched in Amharic, Bulgarian, Cantonese, Galician, Hausa, and Welsh
245. 55th stage (launched October 2024)
246. Crimean Tatar (Latin)
247. French (Canada)
248. Inuktut (Latin)
249. Inuktut (Syllabics)
250. Santali (Ol Chiki)
251. Tshiluba

Translation methodology

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 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. 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.

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). 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. 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, or 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:

• Belarusian (be ↔ ru ↔ en ↔ other);
• Catalan (ca ↔ es ↔ en ↔ other);
• Galician (gl ↔ pt ↔ en ↔ other);
• Haitian Creole (ht ↔ fr ↔ en ↔ other);
• Korean (ko ↔ ja ↔ en ↔ other);
• Slovak (sk ↔ cs ↔ en ↔ other);
• Ukrainian (uk ↔ ru ↔ en ↔ other);
• Urdu (ur ↔ hi ↔ en ↔ other).

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 documents and transcripts. 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.

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.

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, before transitioning to neural machine translation.

Google Translate Community

Google used to have crowdsourcing features for volunteers to be a part of its "Translate Community", intended to help improve Google Translate's accuracy. Volunteers could select up to five languages to help improve translation; users could 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, a Google Crowdsource app was released for Android users, in which translation tasks are offered. There were three ways to contribute. First, Google showed a phrase that one should type in the translated version. Second, Google showed a proposed translation for a user to agree, disagree, or skip. Third, users could suggest translations for phrases where they think they can improve on Google's results. Tests in 44 languages showed that the "suggest an edit" feature led to an improvement in a maximum of 40% of cases over four years. Despite its role in improving translation quality and expanding language coverage, Google closed the Translate Community on March 28, 2024.

Statistical machine translation

Although Google has 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 uses 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 a statistical model that translates texts from one language to another.

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 neural machine translation system used a large end-to-end artificial neural network that attempts to perform deep learning, in particular, long short-term memory networks. GNMT improved 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." According to Google researchers, it translated "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" has been implemented on over a hundred languages supported by Google Translate. 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." The GNMT network attempts 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 in between 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, followed by Bengali, Gujarati, Indonesian, Kannada, Malayalam, Marathi, Punjabi, Tamil and Telugu in April.

Since 2020, Google has phased out GNMT and has implemented deep learning networks based on transformers.

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. 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. 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. A few studies have evaluated Chinese, French, German, and Spanish 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 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. Research conducted in 2011 showed that Google Translate got a slightly higher score than the UCLA minimum score for the English Proficiency Exam. 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. Moreover, a number of languages are translated into a sentence structure and sentence length similar to a human translation. 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.

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, 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.

Limitations

Google Translate, like other automatic translation tools, has its limitations, struggles with polysemy (the multiple meanings a word may have) and multiword expressions (terms that have meanings that cannot be understood or translated by analyzing the individual word units that compose them). A word in a foreign language might have two different meanings in the translated language. This might lead to mistranslation. Additionally, grammatical errors remain a major limitation to the accuracy of Google Translate. Google Translate struggles to differentiate between imperfect and perfect aspects in Romance languages. The subjunctive mood is often erroneous. Moreover, the formal second person (vous) is often chosen, whatever the context. 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. 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. 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, and 2011 and 2012 analyses showed that Italian to English translation is relatively accurate as well. 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.

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

Open-source licenses and components

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 copyrighted by Oxford University Press, United States. Some phrase translations come from Wikitravel.

Reviews

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

Certain texts in Japanese have shown to be translated to "Replying to @sarah_mcdonald(s)" in English, often with no relation to the source text. Examples include "もーるるるるるるるる", "バチバチで草" and "絵にfう". This has been asked on multiple platforms, including YouTube.

References

References

1. Och, Franz Josef. (April 28, 2006). "Statistical machine translation live". [[Google]] Inc..
2. Turovsky, Barak. (November 15, 2016). "Found in translation: More accurate, fluent sentences in Google Translate". [[Google]] Inc..
3. . (April 8, 2020). ["Translations Made Simple: The Usefulness of Translation Apps"](https://www.ulatus.com/translation-blog/most-globally-used-translated-apps/).
4. . ["See which features work with each language"](https://translate.google.com/intl/en/about/languages/). *[[Google]] Inc.*.
5. Caswell, Isaac. (27 June 2024). "110 new languages are coming to Google Translate". [[Google]] Inc..
6. Shankland, Stephen. (May 18, 2013). "Google Translate now serves 200 million people daily". [[Red Ventures]]; [[Paramount Streaming.
7. Turovsky, Barak. (April 28, 2016). "Ten years of Google Translate". [[Google]] Inc..
8. Benjamin, Martin. (April 1, 2019). "How GT Pivots through English".
9. Benjamin, Martin. (April 1, 2019). "Catalan to Spanish Translations".
10. Hofstadter, Douglas. (January 30, 2018). "The Shallowness of Google Translate".
11. Benjamin, Martin. (March 30, 2019). "Source data for Teach You Backwards: An In-Depth Study of Google Translate for 108 Languages".
12. Sommerlad, Joe. (June 19, 2018). "Google Translate: How does the search giant's multilingual interpreter actually work?".
13. Petrovan, Bogdan. (January 14, 2015). "Google Translate just got smarter: Word Lens and instant voice translations in the latest update".
14. (July 26, 2018). "How accurate is Google Translate in 2018?".
15. Corcoran, Kieran. (August 11, 2017). "A British court was forced to rely on Google Translate because it had no interpreter". [[Insider Inc.]], [[Axel Springer SE]].
16. Chidley-Hill, John. (February 21, 2021). "Online petition asks for Cree language to be added to Google Translate". [[CTV News]], [[Bell Media]] (owner).
17. Beattie, Samantha. (February 23, 2021). "Google Translate's Exclusion Of Indigenous Languages A 'Squandered' Opportunity". [[BuzzFeed]].
18. Wiggers, Kyle. (September 30, 2022). "Google appears to have disabled Google Translate in parts of China". [[AOL]].
19. Strumpf, Dan. (October 3, 2022). "Google Pulls Translation App From China". [[The Wall Street Journal]].
20. Joseph, Jibin. (27 June 2024). "Google Translate Adds Support for 110 Languages, Its Largest Expansion Ever".
21. Olga, Kusikova. (28 June 2024). "Стало известно, какие языки добавят в «Google Переводчик». Их больше 100.".
22. . ["Google Translate - A Personal Interpreter on Your Phone or Computer"](https://translate.google.com/intl/en/about/). *[[Google]] Inc.*.
23. . ["Google Translate Help"](https://support.google.com/translate/?hl=en). *Google Inc.*.
24. . ["Translate written words"](https://support.google.com/translate/answer/6142478/?hl=en). *Google Inc.*.
25. . ["Translate documents & webpages"](https://support.google.com/translate/answer/2534559/?hl=en). *Google Inc.*.
26. . ["Translate by speech"](https://support.google.com/translate/answer/6142468/?hl=en). *Google Inc.*.
27. . ["Translate text in other apps"](https://support.google.com/translate/answer/6350658/?hl=en). *Google Inc.*.
28. . ["Translate images"](https://support.google.com/translate/answer/6142483/?hl=en). *Google Inc.*.
29. . ["Translate with handwriting or virtual keyboard"](https://support.google.com/translate/answer/6142469/?hl=en). *Google Inc.*.
30. . ["Translate a bilingual conversation"](https://support.google.com/translate/answer/6142474/?hl=en). *Google Inc.*.
31. . ["Transcribe in Google Translate"](https://support.google.com/translate/answer/9724492/?hl=en). *Google Inc.*.
32. Benjamin, Martin. (March 30, 2019). "Dictionary - When & How to Use Google Translate".
33. Benjamin, Martin. (April 1, 2019). "Ooga Booga: Better than a Dictionary - Qualitative Analysis of Google Translate across 108 Languages".
34. . ["Save translations in a phrasebook"](https://support.google.com/translate/answer/6142480/?hl=en). *Google Inc.*.
35. AK, Sony. (December 5, 2019). "Practical Puppeteer: Playing with Google Translate to translate a text".
36. "Search results for "Google Translate"". [[Mozilla Foundation]].
37. "Google Translate". [[Google]] Inc..
38. Baldwin, Roberto. (October 16, 2014). "Google introduces Google Translate Chrome Extension for inline translations of text". [[Financial Times]].
39. Brinkmann, Martin. (July 19, 2016). "Google Translate Integrated In Google Chrome 5". [[Ghacks]] Technology News.
40. . (February 15, 2010). ["Google Chrome 5 features an integrated Google Translate service"](https://stuff.techwhack.com/8388-google-chrome-5-translate).
41. Wauters, Robin. (February 14, 2010). "Rant: Google Translate Toolbar In Chrome 5 Needs An 'Off' Button". [[AOL]].
42. Turovsky, Barak. (July 29, 2015). "See the world in your language with Google Translate". [[Google]] Inc..
43. Setalvad, Ariha. (July 29, 2015). "Google Translate adds 20 new languages to video text translation". [[Vox Media]].
44. Zhu, Wenzhang. (February 8, 2011). "Introducing the Google Translate app for iPhone". [[Google]] Inc..
45. Hutchison, Allen. (August 7, 2008). "Google Translate now for iPhone". [[Google]] Inc..
46. "Google Translate on the App Store". Google.
47. Hachman, Mark. (January 12, 2011). "Google Translate's New 'Conversation Mode': Hands On". [[Ziff Davis]].
48. Halliday, Josh. (October 13, 2011). "Google extends Android translation tool to 14 languages including Russian and Mandarin". [[The Guardian]].
49. June, Laura. (October 13, 2011). "Google Translate app for Android now has speech to speech translations in 14 languages". [[The Verge]].
50. Velazco, Chris. (October 13, 2011). "Google Translate For Android Gets Upgraded "Conversation Mode"".
51. Turovsky, Barak. (January 14, 2015). "Hallo, hola, olá to the new, more powerful Google Translate app". [[Google]] Inc..
52. Russell, Jon. (January 14, 2015). "Google Translate Now Does Real-Time Voice And Sign Translations On Mobile". [[AOL]].
53. Good, Otávio. (July 29, 2015). "How Google Translate squeezes deep learning onto a phone". [[Google]] Inc..
54. Gush, Andrew. (July 29, 2015). "Google Translate adds video translation support for 25 more languages".
55. Olanoff, Drew. (July 29, 2015). "Google Translate's App Now Instantly Translates Printed Text In 27 Languages". [[AOL]].
56. Benjamin, Martin. (March 30, 2019). "Instant Camera Translation - Introduction: Into the Black Box of Google Translate".
57. Kastrenakes, Jacob. (May 11, 2016). "Google Translate now works inside any app on Android". [[Vox Media]].
58. Feldman, Adam. (June 3, 2011). "Spring cleaning for some of our APIs (Google Code Blog)". [[Google]] Inc..
59. Feldman, Adam. (June 3, 2011). "Spring cleaning for some of our APIs (Google Developers Blog)". [[Google]] Inc..
60. Grunwald, Dave. (May 27, 2011). "BREAKING NEWS! Google to shut down Translate API".
61. "Google Translate API (deprecated)". [[Google]] Inc..
62. Grunwald, Dave. (June 4, 2011). "Google cancels plan to shutdown Translate API. To start charging for translations".
63. Wong, George. (May 27, 2011). "Google gets rid of APIs for Translate and other services".
64. Burnette, Ed. (May 27, 2011). "Google pulls the rug out from under web service API developers, nixes Google Translate and 17 others". [[Red Ventures]]; [[Paramount Streaming.
65. Henderson, Fergus. (May 11, 2010). "Giving a voice to more languages on Google Translate". [[Google]] Inc..
66. Venugopal, Ashish. (May 13, 2010). "Five more languages on translate.google.com". [[Google]] Inc..
67. Uszkoreit, Jakob. (September 30, 2010). "Veni, Vidi, Verba Verti (Official Google Blog)". [[Google]] Inc..
68. (October 1, 2010). "Veni, Vidi, Verba Verti (Google Translate Blog)". [[Google]] Inc..
69. . (December 17, 2010). ["Google picks SVOX for Translate and Dictionary services"](https://www.svox.com/News-Items-Google-picks-SVOX-for-Translate-and-Dictionary-services-.aspx). *SVOX*.
70. Venugopal, Ashish. (June 21, 2011). "Google Translate welcomes you to the Indic web". [[Google]] Inc..
71. Brants, Thorsten. (February 22, 2012). "Tutmonda helplingvo por ĉiuj homoj". [[Google]] Inc..
72. Brants, Thorsten. (September 13, 2012). "Translating Lao". [[Google]] Inc..
73. Crum, Chris. (September 13, 2012). "Google Adds Its 65th Language To Google Translate With Lao".
74. Ong, Josh. (April 19, 2013). "Google Translate Now Supports 66 Languages After Adding Khmer". [[Financial Times]].
75. Noda, Tam. (May 10, 2013). "Google Translate goes Cebuano".
76. Liyanage, Vimukthi. (December 12, 2014). "Google සිංහල පරිවර්ථන සේවය අද සිට ක්‍රියාත්මකයි !".
77. . (February 19, 2016). ["Google can now translate text into Sindhi, Pashto and vice versa"](https://www.dawn.com/news/1240589). *[[Dawn Media Group]]*.
78. . (February 18, 2016). ["Google adds Sindhi to its translate language options"](https://www.dnaindia.com/technology/report-google-adds-sindhi-to-its-translate-language-options-2179229). *[[Essel Group]]*.
79. . (February 18, 2016). ["Google adds Sindhi to its translate language options"](https://in.news.yahoo.com/google-adds-sindhi-translate-language-options-113113260.html). *[[Yahoo!]]*.
80. Ahmed, Ali. (February 18, 2016). "Google Translate now includes Sindhi and Pashto".
81. Shu, Catherine. (February 17, 2016). "Google Translate Now Has More Than 100 Languages And Covers 99 Percent Of The Online Population". [[AOL]].
82. Sandilo, Tariq. (February 21, 2016). "گوگل تي سنڌي ٻولي".
83. Humphries, Matthew. (February 27, 2020). "Google Translate Adds 5 New Languages". [[Ziff Davis]].
84. Wilde, Damien. (May 11, 2022). "Google Translate adds support for 24 new languages, now supports over 130".
85. Li, Abner. (27 June 2024). "Google Translate adding support for 110 new languages, including Cantonese".
86. (18 October 2024). "Crimean Tatar language in Latin script now available in Google Translate". Ukrainska Pravda.
87. "Language expansion". Google Inc..
88. Och, Franz Josef. (September 12, 2005). "Statistical Machine Translation: Foundations and Recent Advances". Asia-Pacific Association for Machine Translation.
89. . (September 12–16, 2005). ["MT Summit X: The Tenth Machine Translation Summit (proceedings)"](https://books.google.com/books?id=oooQAAAACAAJ). *Asia-Pacific Association for Machine Translation*.
90. . (July 29, 2014). ["Franz Och, Ph.D., Expert in Machine Learning and Machine Translation, Joins Human Longevity, Inc. as Chief Data Scientist"](https://www.humanlongevity.com/franz-och-ph-d-expert-in-machine-learning-and-machine-translation-joins-human-longevity-inc-as-chief-data-scientist/). *Human Longevity, Inc.*.
91. link. (December 31, 2021 ''{{lang). fr. le mot 'obvious' n'est pas français → {{lang. ru. "очевидными" слово не французское''
92. link. (February 3, 2022 ''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 "{{lang). de. außergewöhnlich" however will be translated twice.''
93. (January 31, 2011). "MT on and for the Web".
94. P.Y.. (October 25, 2010). "Wrong translation to Ukrainian language".
95. fr. tu. fr. vous. link. (December 31, 2021 ''{{lang). fr. Je vous aime. Tu es ici. You are here. → {{lang. ru. Я люблю тебя. Вы здесь. Вы здесь.''
96. Adams, Tim. (December 19, 2010). "Can Google break the computer language barrier?".
97. Tanner, Adam. (March 28, 2007). "Google seeks world of instant translations". [[Thomson Reuters]].
98. 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.
99. "Inside Google Translate (old)". [[Google]] Inc..
100. Chitu, Alex. (October 22, 2007). "Google Switches to Its Own Translation System". [[Google]] Inc..
101. Schwartz, Barry. (October 23, 2007). "Google Translate Drops Systran For Home Brewed Translation".
102. Southern, Matt. (July 28, 2014). "Google Seeks Community Help To Improve Google Translate".
103. Kelman, Sveta. (July 25, 2014). "Translate Community: Help us improve Google Translate!". [[Google]] Inc..
104. "Help Us Improve the Google Translate Tool". [[Google]] Inc..
105. Lardinois, Frederic. (July 25, 2014). "Google Wants To Improve Its Translations Through Crowdsourcing". [[AOL]].
106. Summers, Nick. (July 25, 2014). "Google sets up a community site to help improve Google Translate". [[Financial Times]].
107. "Google Translate Community FAQ".
108. Whitwam, Ryan. (August 29, 2016). "New Google Crowdsource app asks you to help with translation and text transcription a few seconds at a time".
109. Shankland, Stephen. (August 29, 2016). "New Crowdsource app lets you work for Google for free". [[Red Ventures]]; [[Paramount Streaming.
110. Benjamin, Martin. (April 1, 2019). "Myth 5: Google Translate learns from its users - Qualitative Analysis of Google Translate across 108 Languages".
111. Lange, William. (February 7, 2017). "Statistical Vs Neural Machine Translation". United Language Group.
112. . ["Statistical Vs. Neural Machine Translation"](https://unitedlanguagegroup.com/blog/statistical-vs-neural-machine-translation/). *United Language Group*.
113. (September 27, 2016). "A Neural Network for Machine Translation, at Production Scale". [[Google]] Inc..
114. (November 22, 2016). "Zero-Shot Translation with Google's Multilingual Neural Machine Translation System". [[Google]] Inc..
115. Fewster, Gil. (January 5, 2017). "The mind-blowing AI announcement from Google that you probably missed.". [[freeCodeCamp]].
116. (November 15, 1997). "Long short-term memory". [[Neural Computation (journal).
117. (October 1, 2000). "Learning to Forget: Continual Prediction with LSTM". [[Neural Computation (journal).
118. Cade, Metz. (September 27, 2016). "An Infusion of AI Makes Google Translate More Powerful Than Ever".
119. McDonald, Chris. (January 7, 2017). "Ok slow down".
120. Davenport, Corbin. (March 6, 2017). "Google Translate now uses neural machine translation for some languages".
121. Hager, Ryne. (April 25, 2017). "Google adds Indonesian and eight new Indian languages to its neural machine translation".
122. (June 8, 2020). "Recent Advances in Google Translate". [[Google]] Inc..
123. Benjamin, Martin. (March 30, 2019). "The 5 conditions for satisfactory approximations with Google Translate - Conclusions: Real Data, Fake Data & Google Translate".
124. Benjamin, Martin. (March 30, 2019). "Empirical Evaluation of Google Translate across 107 Languages".
125. Benjamin, Martin. (March 30, 2019). "Non-English Pairs - Empirical Evaluation of Google Translate across 107 Languages".
126. (April 2011). "An Analysis of Google Translate Accuracy". Translation Journal.
127. (May 3, 2014). "Comparison of Google Translation with Human Translation". FLAIRS Conference.
128. Benjamin, Martin. (April 1, 2019). "Polysemy in top 100 Oxford English Corpus words within Wiktionary".
129. Benjamin, Martin. (April 1, 2019). "Polysemy – words with multiple meanings - The Astounding Mathematics of Machine Translation".
130. Benjamin, Martin. (April 1, 2019). "Party terms (or multiword expressions) – words that play together - The Astounding Mathematics of Machine Translation".
131. (May 31, 2019). "A Study of Google Translate Translations: An Error Analysis of Indonesian-to-English Texts".
132. (December 15, 2017). "Exploring the Differences between Human and Machine Translation". [[Western Washington University]].
133. Shen, Ethan. (June 2010). "Comparison of online machine translation tools".
134. Pecoraro, Christopher. (August 17, 2011). "Microsoft Bing Translator and Google Translate Compared".
135. Pecoraro, Christopher. (January 30, 2012). "Microsoft Bing Translator and Google Translate compared (update)".
136. . ["Open source components and licenses."](https://translate.google.com/intl/en/about/license/). *[[Google]] Inc.*.
137. Nielsen, Michael A.. (October 3, 2011). "Reinventing discovery: the new era of networked science". [[Princeton University Press]].
138. Gomes, Lee. (July 22, 2010). "Google Translate Tangles With Computer Learning".
139. Weinberg, Nathan. (September 10, 2007). "Google Translates Ivan the Terrible as "Abraham Lincoln"".
140. Twisted Translations. (February 10, 2015). "Google Translate Sings: "Bohemian Rhapsody" by Queen". [[Google]] Inc..
141. Topolyanskaya, Alyona. (January 28, 2010). "Google Lost in Translation".
142. Kincaid, Jason. (August 7, 2009). "Translation Party: Tapping Into Google Translate's Untold Creative Genius". [[AOL]].
143. "Google Translate".
144. Elle Stone. (2024-12-18). "Weird Google Translation - Replying to Sarah McDonald {{!}} Weird Wednesday".