Microsoft Translator
{{Infobox website
| name = Microsoft Translator
| logo = 130px
| logo_caption = Logo and favicon of Microsoft Translator, which appears along the title in the web browser
| url = {{URL|https://microsoft.com/translator}}
{{URL|https://www.bing.com/translator}}
| ipv6 = Yes
| type = Machine translation
| registration = Optional
| language = {{:Microsoft Translator}} languages; see below
| owner = Microsoft
| launch_date =
| current_status = Active
}}{{short description|Machine translation cloud service by Microsoft}}
Microsoft Translator or Bing Translator is a multilingual machine translation cloud service provided by Microsoft. Microsoft Translator is a part of Microsoft Cognitive Services{{Cite book|last=Carmen.|first=Steiner|url=http://worldcat.org/oclc/81702109|title=Pilotstudie: über die Funktion des Anhebens der Augenbrauen in der Deutschschweizerischen Gebärdensprache DSGS|date=2000|publisher=Verein zur Unterstützung der Gebärdensprache der Gehörlosen|oclc=81702109}} and integrated across multiple consumer, developer, and enterprise products, including Bing, Microsoft Office, SharePoint, Microsoft Edge, Microsoft Lync, Yammer, Skype Translator, Visual Studio, and Microsoft Translator apps for Windows, Windows Phone, iPhone and Apple Watch, and Android phone and Android Wear.
Microsoft Translator also offers text and speech translation through cloud services for businesses. Service for text translation via the Translator Text API ranges from a free tier supporting two million characters per month to paid tiers supporting billions of characters per month.{{cite web|title=Azure Data Marketplace- Microsoft Translator|url=https://datamarket.azure.com/dataset/bing/microsofttranslator|access-date=2014-12-08|archive-url=https://web.archive.org/web/20180206203347/http://datamarket.azure.com/dataset/bing/microsofttranslator|archive-date=2018-02-06|url-status=dead}} Speech translation via Microsoft Speech services is offered based on the time of the audio stream.
The service supports text translation between many languages and language varieties. It also supports several speech translation systems that currently power the Microsoft Translator live conversation feature, Skype Translator, and Skype for Windows Desktop, and the Microsoft Translator Apps for iOS and Android.{{cite web|title=Microsoft Translator- Languages|website=Microsoft|url=https://www.microsoft.com/en-us/translator/languages.aspx|access-date=January 6, 2023}}
Development
= History =
The first version of Microsoft's machine translation system was developed between 1999 and 2000 within Microsoft Research. This system was based on semantic predicate-argument structures known as logical forms (LF) and was spun from the grammar correction feature developed for Microsoft Word. This system was eventually used to translate the entire Microsoft Knowledge Base into Spanish, French, German, and Japanese.{{cite web|title=Microsoft Research- Arul Menezes|url=http://research.microsoft.com/en-us/people/arulm/}}
Microsoft's approach to machine translation, like most modern machine translation systems, is "data driven":{{cite web|title=Microsoft Research- Machine Translation|url=http://research.microsoft.com/en-us/projects/mt/}} rather than relying on writing explicit rules to translate natural language, algorithms are trained to understand and interpret translated parallel texts, allowing them to automatically learn how to translate new natural language text. Microsoft's experience with the LF system led directly to a treelet translation system that simplified the LF to dependency trees and eventually to an order template model, significantly improving in speed and enabling the incorporation of new target languages. {{Citation needed|date=April 2019}}
The consumer-facing translation site known as Bing Translator (previously known as Windows Live translator) was launched in 2007 and provides free text and website translations on the web. Text is translated directly within the Bing Translator webpage while websites are translated through the Bilingual Viewer tools.{{Citation needed|date=April 2019}}
In 2011, the service was extended to include numerous Microsoft Translator products through a cloud-based application programming interface, which supports products available to both consumer and enterprise users. An additional speech translation capability was introduced in March 2016.{{cite web|url=http://blogs.msdn.com/b/translation/archive/2016/03/30/microsoft-translator-brings-end-to-end-speech-translation-to-everyone-with-the-world-s-first-speech-translation-api.aspx|title=Microsoft Translator brings end-to-end speech translation to everyone with the world's first Speech Translation API}}
In May 2018, an update to the API was introduced. This new version offered neural machine translation as the default method of translating. In addition to translation, the new version features transliteration and a bilingual dictionary to look up words to find alternative translations and view examples in sentences.{{cite web|url=https://www.microsoft.com/en-us/translator/translatorapi.aspx/|title=Microsoft Translator- Translator Text API|website=Microsoft|url-status=dead|archive-url=https://web.archive.org/web/20190902184414/https://www.microsoft.com/en-us/translator/business/translator-api/|archive-date=2019-09-02}}
Speech translation was integrated into Microsoft Speech services in September 2018, providing end-to-end speech, speech-to-text, and text-to-speech translation.{{Citation needed|date=April 2019}}
= Translation methodology and research =
Microsoft Translator uses machine translation to create instantaneous translations from one natural language to another. This system is based on four distinct areas of computer learning research seen below.
class="wikitable" | |
Type of learning | Impact on translation |
---|---|
Neural networks Neural machine translation | Neural networks try to mimic how the brain works to translate between languages. At a high level, neural network translation works in two stages. First, a first stage models the word that needs to be translated based on the context of this word (and its possible translations) within the full sentence. Second, the neural network translates this word model (not the word itself but the model the neural networks built of it), within the context of the sentence, into the other language.{{cite web|title=What is neural network based translation?|url=https://microsofttranslator.uservoice.com/knowledgebase/articles/1099027-what-is-neural-network-based-translation|access-date=2016-11-28|archive-date=2021-02-08|archive-url=https://web.archive.org/web/20210208195336/https://microsofttranslator.uservoice.com/knowledgebase/articles/1099027-what-is-neural-network-based-translation|url-status=dead}} Neural machine translation is the default translation method for the Microsoft Translator API. |
Syntax-based SMT {{main|Statistical machine translation}} | Syntax-based translation is based on the idea of translating syntactic units, rather than a word or string of words. Microsoft has used syntax-based SMT to translate much of its computer-related texts from English into multiple target languages. Ongoing research in this area has produced improvements in word inflections and word ordering. |
Phrase-based SMT | In phrase-based SMT, the machine learns correspondence between languages from parallel text without the aid of linguist knowledge. This produces better translations in less time than other systems. |
Bitext word alignment | SMT systems rely on existing translated data to learn how to automatically translate from one language to another. To train the systems, identifying word correspondences (or word alignments) is crucial. Microsoft has developed work in both discriminative{{cite web|title=A Discriminative Framework for Bilingual Word Alignment|url=http://www.aclweb.org/anthology-new/H/H05/H05-1011.pdf|archive-url=https://web.archive.org/web/20080720142028/http://www.aclweb.org/anthology-new/H/H05/H05-1011.pdf|url-status=dead|archive-date=2008-07-20}} and generative{{cite web|title=Using Word Dependent Transition Models in HMM based Word Alignment for Statistical Machine Translation|url=http://research.microsoft.com/en-us/projects/mt/w07-0711.pdf}} approaches to word alignment, resulting in faster algorithms and higher quality and translations. |
Language modeling | Language modeling uses n-gram models to construct comprehensible translations in the target language. This ensures that the output translation is fluent and readable. |
= Accuracy =
The quality of Microsoft Translator's machine translation outputs are evaluated using a method called the BLEU score.{{cite web|title=Microsoft Translator Hub: Discussion of BLEU Score| date=23 May 2013 |url=http://research.microsoft.com/apps/video/default.aspx?id=193716}}
BLEU (Bilingual Evaluation Understudy) is an algorithm for evaluating the quality of text which has been machine-translated from one natural language to another. Quality is considered to be the correspondence between a machine's output and that of a human. BLEU was one of the first metrics to achieve a high correlation with human judgments of quality, and remains one of the most popular automated and inexpensive metrics.
Because machine translation is based on statistical algorithms rather than human translators, the automatic translations it produces are not always entirely accurate. Microsoft Translator has introduced various feedback features, such as the Collaborative Translation Framework, into its products to allow users to suggest alternative translations. These alternative translations are then integrated into the Microsoft Translator algorithms to improve future translations.
In November 2016, Microsoft Translator introduced translation using deep neural networks in nine of its highest-traffic languages, including all of its speech languages and Japanese. Neural networks provide better translation than industry standard statistical machine learning.{{cite web|title=Microsoft Translator launching Neural Network based translations for all its speech languages|date=16 November 2016|url=https://blogs.msdn.microsoft.com/translation/2016/11/15/microsoft-translator-launching-neural-network-based-translations-for-all-its-speech-languages/}}
Core products
Microsoft Translator is a cloud-based API that is integrated into numerous Microsoft products and services.{{cite web|title=Microsoft Translator- Products|website=Microsoft|url=http://www.microsoft.com/translator/products.aspx}} The Translator API can be used on its own and can be customized for use in a pre-publishing or post-publishing environment. The API, which is available through subscription, is free for lower translation volumes, and is charged according to a tiered payment system for volumes exceeding two million characters per month. The remaining core products are available for free.
= Microsoft Translator cloud translation =
The Microsoft Translator is a cloud-based automatic translation service that can be used to build applications, websites, and tools requiring multi-language support.
- Text translation: The Microsoft Translator Text API can be used to translate text into any of the languages supported by the service.
- Speech translation: Microsoft Translator is integrated into Microsoft Speech services which is an end-to-end REST based API that can be used to build applications, tools, or any solution requiring multi-languages speech translation. Speech to speech translation is available to or from any of the conversation languages, and speech to text translation is available from the conversation languages into any of the Microsoft Translator-supported language systems.
= Custom Translator =
Custom Translator is a feature of the Microsoft Translator services that allows enterprises, app developers, and language service providers to build neural translation systems that understand the terminology used in their own business and industry. The customized translations can then be delivered into existing applications, workflows and websites using a normal call to the Microsoft Translator API. Custom Translator can be used when translating text with the Microsoft Translator Text API and when translating speech with Microsoft Speech services.{{cite web|title=Microsoft Translator- Customization|website=Microsoft|url=https://www.microsoft.com/en-us/translator/customization.aspx}}
= Live feature =
A personal universal translator that enables up to 500 people to have live, multi-device, multi-language, in-person translated conversations.{{cite web|title=Microsoft Translator live feature|website=Microsoft|date=18 July 2023 |url=https://www.microsoft.com/en-us/translator/live.aspx}} This feature is currently free and available in the Microsoft Translator apps (Android, iOS or Windows) and from the Microsoft Translator website.
= Microsoft Translator Hub =
The Microsoft Translator Hub allows enterprises and language service providers to build their own translation systems that understand business- and industry-specific terminology.{{cite web|title=Microsoft Translator- Translator Hub|website=Microsoft|url=http://www.microsoft.com/translator/translator-hub.aspx}} The Hub can also be used in conjunction with the CTF, allowing administrators to approve CTF results and add them directly to the Hub. The Microsoft Translator Hub is only available for statistical machine translation and cannot be used with the newest version of the Microsoft Translator API.
The Hub has also been used for language preservation, allowing communities to create their own language translation systems for language and cultural preservation.{{cite web|title=Where Language Meets the World: Microsoft Translator Hub|website = YouTube| date=4 September 2014 |url=https://www.youtube.com/watch?v=UnROjeEHqDE&list=PLD7HFcN7LXRd4kd2XgZjIbQ8TwTC32Zc9&index=9 |archive-url=https://ghostarchive.org/varchive/youtube/20211220/UnROjeEHqDE |archive-date=2021-12-20 |url-status=live}}{{cbignore}} The Hub has been used to create translation systems for languages such as Hmong, Mayan, Nepali, and Welsh.
= Multilingual App Toolkit (MAT) =
The Multilingual App Toolkit (MAT) is an integrated Visual Studio tool, which allows developers to streamline localization workflows of their Windows, Windows Phone and desktop apps.{{cite web|title=Microsoft Translator- Multilingual App Toolkit|website=Microsoft|url=http://www.microsoft.com/translator/multilingual-app-toolkit.aspx}} MAT improves localization of file management, translation support, and editing tools.
Bing Microsoft Translator web app
{{update|section|date=February 2019}}
{{Main|Bing (search engine)#Translator}}
{{Infobox website
|name = Microsoft Translator
|url = {{URL|https://www.bing.com/translator/}}
|ipv6 = Yes
|commercial =
|type = Neural machine translation
|registration = Optional
|language = See below
|num_users =
|owner = Microsoft
|launch_date = {{start date and age|2009|06|03}} (as Live Search Translator)
|current_status = Active
}}
Bing Microsoft Translator (previously Live Search Translator, Windows Live Translator, and Bing Translator){{cite book|last1=Antoniou|first1=Grigoris|last2=Grobelnik|first2=Marko|last3=Simperl|first3=Elena|last4=Parsia|first4=Bijan|last5=Plexousakis|first5=Dimitris|last6=de Leenheer|first6=Pieter|last7=Pan|first7=Jeff Z.|title=The Semantic Web: Research and Applications.|date=2011|publisher=Springer Science+Business Media|location=Berlin|isbn=9783642210334|page=341}} is a user-facing translation portal provided by Microsoft as part of its Bing services to translate texts or entire web pages into different languages. All translation pairs are powered by the Microsoft Translator, a neural machine translation platform and web service, developed by Microsoft Research, as its backend translation software. Two transliteration pairs (between simplified Chinese and traditional Chinese) are provided by Microsoft's Windows International team.{{cite web
|url = http://blogs.msdn.com/translation/archive/2008/09/08/translation-powered-by-microsoft-translator.aspx
|title = Translation powered by....Microsoft Translator!
|work = Microsoft Translator (and Bing Translator) Official Team Blog
|publisher = Microsoft Corporation
|date = 8 September 2008
|access-date = 21 October 2010
}}
File:Windows Live Translator Bilingual Viewer.jpg translation of the French Wikipedia's main page]]
Bing Translator can translate phrases entered by the user or acquire a link to a web page and translate it entirely. When translating an entire web page, or when the user selects "Translate this page" in Bing search results, the Bilingual Viewer is shown, which allows users to browse the original web page text and translation in parallel, supported by synchronized highlights, scrolling, and navigation.{{cite web|title=About Bing Translator|url=http://www.bing.com/translator/help/|website=Bing Translator|publisher=Microsoft|access-date=20 December 2014}} Four Bilingual Viewer layouts are available:
- Side by side
- Top and bottom
- Original with hover translation
- Translation with hover original
Bing Translator integrates with several other Microsoft products. The following is a table of products into which Bing Translator could be integrated:
class="wikitable plainrowheaders" |
! scope=col | Integrates into ! scope=col | Means of integration |
scope=row | Bing Instant Answers
| Already integrated |
---|
scope=row | Internet Explorer
| An Accelerator for Internet Explorer 8 or higher |
Supported products
Through its core product offerings, Microsoft Translator supports the translation features of many Microsoft products at the consumer and enterprise levels. These products fall broadly into three categories{{cite web|title= Microsoft Translator- Products|website=Microsoft|url=http://www.microsoft.com/translator/products.aspx}}—communication products, Microsoft Office, and apps.
{{col-begin|width=95%}}
{{col-3}}
= Communication =
{{col-3}}
= Microsoft Office =
= Apps =
- Web app (translator.microsoft.com)
- Windows and Windows 10
- Windows Phone
- iPhone and Apple Watch
- Android phone and Android Wear
- Kindle Fire
- Skype Translator
- Microsoft Edge
- Microsoft SwiftKey
{{col-end}}
Deprecated products
= Collaborative Translation Framework (CTF) =
The Collaborative Translation Framework (CTF) is an extension of the Microsoft Translator API that allows post-publishing improvement of translated text.{{cite web|title=Microsoft Translator- Collaborative Translation Framework|website=Microsoft|url=http://www.microsoft.com/translator/collaborative-translation-framework.aspx|archive-url=https://web.archive.org/web/20150330064733/http://www.microsoft.com/translator/collaborative-translation-framework.aspx|archive-date=30 March 2015|url-status=dead}} By using the CTF, readers have the ability to suggest alternative translations to those provided by the API, or vote on previously offered alternatives. This information is then delivered to the API to improve future translations.
= Translator Web Widget =
The Translator Web Widget is a translation tool that can be added to web pages by pasting a predefined snippet of JavaScript code into the page.{{cite web|title=Microsoft Translator- Translator Web Widget|website=Microsoft|url=http://www.microsoft.com/translator/translator-web-widget.aspx}} The web widget is offered for free by Microsoft, and supports both pre-publishing customized translations using the Translator Hub, and post-publishing improvements using the Collaborative Translation Framework.
Supported languages
{{As of|{{CURRENTMONTHNAME}} {{CURRENTYEAR}}}}, Microsoft Translator supports
{{div col|colwidth=16em}}
- Acehnese (Latin)
- Afrikaans
- Albanian
- Amharic
- Arabic
- Arabic (Egyptian)
- Arabic (Moroccan)
- Arabic (Romanized)
- Armenian
- Assamese
- Asturian
- Azerbaijani
- Balinese
- Bangla
- Bashkir
- Basque
- Batak Toba
- Belarusian
- Bhojpuri
- Bikol
- Bodo
- Bosnian
- Bulgarian
- Cantonese (Traditional)
- Catalan
- Cebuano
- Chhattisgarhi
- Chinese (Literary)
- Chinese Simplified
- Chinese Traditional
- Corsican
- Croatian
- Czech
- Danish
- Dari
- Divehi
- Dogri
- Dutch
- English
- English (United Kingdom)
- Esperanto
- Estonian
- Faroese
- Fijian
- Filipino
- Finnish
- French
- French (Canada)
- Frisian
- Friulian
- Galician
- Ganda
- Georgian
- German
- Greek
- Gujarati
- Haitian Creole
- Hausa
- Hebrew
- Hiligaynon
- Hindi
- Hmong Daw
- Hungarian
- Iban
- Icelandic
- Igbo
- Ilocano
- Indonesian
- Inuinnaqtun
- Inuktitut
- Inuktitut (Latin)
- Irish
- Italian
- Jamaican Patois
- Japanese
- Javanese
- Kabuverdianu
- Kannada
- Kapampangan
- Kashmiri
- Kazakh
- Khmer
- Kinyarwanda
- Klingon (Latin)
- Konkani
- Korean
- Krio
- Kurdish (Central)
- Kurdish (Northern)
- Kyrgyz
- Lao
- Latin
- Latvian
- Ligurian (Genoese)
- Limburgish
- Lingala
- Lithuanian
- Lombard
- Lower Sorbian
- Luxembourgish
- Macedonian
- Maithili
- Malagasy
- Malay
- Malayalam
- Maltese
- Marathi
- Marwari
- Mauritian Creole
- Minangkabau (Latin)
- Mongolian (Cyrillic)
- Mongolian (Traditional)
- Myanmar (Burmese)
- Māori
- Nepali
- Norwegian
- Norwegian Nynorsk
- Nyanja
- Occitan
- Odia
- Papiamento
- Pashto
- Persian
- Polish
- Portuguese (Brazil)
- Portuguese (Portugal)
- Punjabi (Gurmukhi)
- Punjabi (Shahmukhi)
- Querétaro Otomi
- Romanian
- Rundi
- Russian
- Samoan
- Sanskrit
- Sardinian
- Serbian (Cyrillic)
- Serbian (Latin)
- Sesotho
- Sesotho sa Leboa
- Setswana
- Seychelles French Creole
- Shona
- Sicilian
- Sindhi
- Sinhala
- Slovak
- Slovenian
- Somali
- Spanish
- Sundanese
- Swahili
- Swedish
- Tahitian
- Tajik
- Tamil
- Tatar
- Telugu
- Tetum
- Thai
- Tibetan
- Tigrinya
- Tok Pisin
- Tongan
- Turkish
- Turkmen
- Ukrainian
- Upper Sorbian
- Urdu
- Uyghur
- Uzbek (Latin)
- Venetian
- Vietnamese
- Waray
- Welsh
- Xhosa
- Yiddish (Eastern)
- Yoruba
- Yucatec Maya
- Zulu
{{div col end}}
= Supported languages by text-to-speech =
As of {{CURRENTMONTHNAME}} {{CURRENTYEAR}}, Microsoft Translate supports 76 languages for the text-to-speech tool.
- Afrikaans
- Amharic
- Arabic
- Arabic (Egyptian)
- Arabic (Moroccan)
- Assamese
- Asturian
- Bangla
- Belarusian
- Bulgarian
- Cantonese (Traditional)
- Catalan
- Chinese Simplified
- Chinese Traditional
- Croatian
- Czech
- Danish
- Dutch
- English
- English (United Kingdom)
- Estonian
- Finnish
- French
- French (Canada)
- German
- Greek
- Gujarati
- Hebrew
- Hindi
- Hungarian
- Icelandic
- Indonesian
- Inuktitut
- Inuktitut (Latin)
- Irish
- Italian
- Japanese
- Javanese
- Kannada
- Kazakh
- Khmer
- Korean
- Lao
- Latvian
- Lithuanian
- Macedonian
- Malay
- Malayalam
- Maltese
- Marathi
- Myanmar (Burmese)
- Norwegian
- Pashto
- Persian
- Polish
- Portuguese (Brazil)
- Portuguese (Portugal)
- Romanian
- Russian
- Serbian (Cyrillic)
- Sesotho
- Setswana
- Slovak
- Slovenian
- Spanish
- Sundanese
- Swedish
- Tamil
- Telugu
- Thai
- Turkish
- Ukrainian
- Urdu
- Uzbek (Latin)
- Vietnamese
- Welsh
Community partners
Microsoft Translator has engaged with community partners to increase the number of languages and to improve overall language translation quality. Below is a list of community partners that Microsoft Translator has teamed with.{{cite web|title=Translator Community Partners|website=Microsoft|url=https://www.microsoft.com/en-us/translator/business/community/}}
- CNGL Centre for Global Intelligent Content
- Hmong Language Partners {{En dash}} Hmong Daw
- Jawaharlal Nehru University {{En dash}} Urdu
- Senedd Cymru (the Welsh Parliament, partnered as the National Assembly for Wales) {{En dash}} Welsh
- Tilde {{En dash}} Estonian, Latvian, Lithuanian
- Translators Without Borders {{En dash}} Swahili
- Appen {{En dash}} Filipino (Tagalog), Malagasy, Samoan, Tahitian, Tongan
- Government of Nunavut {{En dash}} Inuktitut
- Auckland University of Technology {{En dash}} Māori
- Waikato University {{En dash}} Māori
- Government of the State of Querétaro {{En dash}} Querétaro Otomi
- Klingon Language Institute {{En dash}} Klingon
Additionally, Microsoft has teamed with the Klingon Language Institute, which promotes the constructed language, Klingon, which is used within the fictional Star Trek universe produced by Paramount and CBS Studios. Klingon has been supported by Microsoft Translator since May 2013.{{cite web|title=New Bing Translator Option Lets You Translate... Klingon|date=14 May 2013 |url=http://www.startrek.com/article/new-bing-translator-option-lets-you-translate-klingon}}
See also
{{portal|Language}}
{{div col|colwidth=30em}}
- Machine translation
- Speech synthesis
- Comparison of machine translation applications
- Lernout & Hauspie
- Babel Fish (discontinued; redirects to main Yahoo! site)
- PlainTalk
- NeoSpeech
- Loquendo
- Nuance Communications
- Microsoft text-to-speech voices
- Google Translate
- Yandex Translate
{{div col end}}
References
{{reflist|colwidth=30em}}
External links
- {{cite web|url= https://www.bing.com/translator/|title= Free Translator for Text or Internet|website= microsofttranslator.com}} (copyright of Microsoft)
- {{cite web|url= https://www.microsoft.com/en-us/legal/intellectualproperty/permissions/default.aspx/|title= Use of Microsoft Copyrighted Content|website= Microsoft}}
- {{cite web|url= https://translator.microsoft.com/help/bing/#TranslationFeatures|title= Translator for Bing. Help & FAQs.|access-date= Aug 12, 2018|language= en|archive-url= https://web.archive.org/web/20180812203740/https://translator.microsoft.com/help/bing|archive-date= August 12, 2018|url-status= live}}
= SW development =
- {{cite web|url= http://blogs.msdn.com/b/translation/|title= Microsoft Translator Team Blog|language= en}}
- {{cite web|url= http://msdn.microsoft.com/en-us/library/dd576287.aspx/|title= Microsoft Translator on the Microsoft Developer Network|language= en}}
{{Microsoft}}
{{Authority control}}
Category:Machine translation software
Category:Natural language processing software
Category:Universal Windows Platform apps
Category:Android (operating system) software
Category:Microsoft Edge extensions