Microsoft Translator

Last updated
Microsoft Translator
Microsoft Translator Logo.svg
Logo and favicon of Microsoft Translator, which appears along the title in the web browser
Type of site
Machine translation
Available insee below
Owner Microsoft
URL microsoft.com/translator
RegistrationOptional
Current statusActive

Microsoft Translator is a multilingual machine translation cloud service provided by Microsoft. Microsoft Translator is a part of Microsoft Cognitive Services [1] 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.

Contents

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. [2] 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. [3]

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. [4]

Microsoft's approach to machine translation, like most modern machine translation systems, is "data driven": [5] 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 ]

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 ]

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. [6]

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. [7]

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 ]

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. [5]

Type of learningImpact 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. [8] Neural machine translation is the default translation method for the Microsoft Translator API.
Syntax-based SMT
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 SMTIn 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 [9] and generative [10] 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. [11]

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. [12]

Core products

Microsoft Translator is a cloud-based API that is integrated into numerous Microsoft products and services. [13] 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. [2] 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.

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. [14]

Live feature

A personal universal translator that enables up to 500 people to have live, multi-device, multi-language, in-person translated conversations. [15] 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. [16] 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. [17] 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. [18] MAT improves localization of file management, translation support, and editing tools.

Bing Microsoft Translator web app

Microsoft Translator
Type of site
Neural machine translation
Available inSee below
Owner Microsoft
URL www.bing.com/translator/
RegistrationOptional
LaunchedJune 3, 2009;14 years ago (2009-06-03) (as Live Search Translator)
Current statusActive

Bing Microsoft Translator (previously Live Search Translator, Windows Live Translator, and Bing Translator) [19] 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. [20]

The Bilingual Viewer showing the English translation of the French Wikipedia's main page Windows Live Translator Bilingual Viewer.jpg
The Bilingual Viewer showing the English 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. [21] Four Bilingual Viewer layouts are available: [21]

Bing Translator integrates with several other Microsoft products. The following is a table of products into which Bing Translator could be integrated:

Integrates intoMeans of integration
Bing Instant Answers Already integrated
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 [22] —communication products, Microsoft Office, and apps.

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. [23] 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. [24] 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 March 2024, Microsoft Translator supports 135 languages and language varieties. [3] The list of supported languages is available at the Microsoft Translator website and can also be retrieved programmatically through the cloud services. [25]

  1. Afrikaans
  2. Albanian
  3. Amharic
  4. Arabic
  5. Armenian
  6. Assamese
  7. Azerbaijani
  8. Bangla
  9. Bashkir
  10. Basque
  11. Bhojpuri
  12. Bodo
  13. Bosnian
  14. Bulgarian
  15. Cantonese (Traditional)
  16. Catalan
  17. Chhattisgarhi
  18. Chinese (Literary)
  19. Chinese (Simplified)
  20. Chinese (Traditional)
  21. Croatian
  22. Czech
  23. Danish
  24. Dari
  25. Divehi
  26. Dogri
  27. Dutch
  28. English
  29. Estonian
  30. Faroese
  31. Fijian
  32. Filipino
  33. Finnish
  34. French
  35. French (Canada)
  36. Galician
  37. Georgian
  38. German
  39. Greek
  40. Gujarati
  41. Haitian Creole
  42. Hausa
  43. Hebrew
  44. Hindi
  45. Hmong Daw
  46. Hungarian
  47. Icelandic
  48. Igbo
  49. Indonesian
  50. Inuinnaqtun
  51. Inuktitut
  52. Inuktitut (Latin)
  53. Irish
  54. Italian
  55. Japanese
  56. Kannada
  57. Kashmiri
  58. Kazakh
  59. Khmer
  60. Kinyarwanda
  61. Klingon (Latin)
  62. Klingon (plqaD)
  63. Konkani
  64. Korean
  65. Kurdish (Central)
  66. Kurdish (Northern)
  67. Kyrgyz
  68. Lao
  69. Latvian
  70. Lingala
  71. Lithuanian
  72. Lower Sorbian
  73. Luganda
  74. Macedonian
  75. Maithili
  76. Malagasy
  77. Malay
  78. Malayalam
  79. Maltese
  80. Manipuri
  81. Marathi
  82. Mongolian (Cyrillic)
  83. Mongolian (Traditional)
  84. Myanmar (Burmese)
  85. Māori
  86. Nepali
  87. Norwegian
  88. Nyanja
  89. Odia
  90. Pashto
  91. Persian
  92. Polish
  93. Portuguese (Brazil)
  94. Portuguese (Portugal)
  95. Punjabi (Gurmukhi)
  96. Querétaro Otomi
  97. Romanian
  98. Rundi (Kirundi)
  99. Russian
  100. Samoan
  101. Serbian (Cyrillic)
  102. Serbian (Latin)
  103. Sesotho
  104. Sesotho sa Leboa
  105. Setswana
  106. Shona
  107. Sindhi
  108. Sinhala
  109. Slovak
  110. Slovenian
  111. Somali
  112. Spanish
  113. Swahili
  114. Swedish
  115. Tahitian
  116. Tamil
  117. Tatar
  118. Telugu
  119. Thai
  120. Tibetan
  121. Tigrinya
  122. Tongan
  123. Turkish
  124. Turkmen
  125. Ukrainian
  126. Upper Sorbian
  127. Urdu
  128. Uyghur
  129. Uzbek (Latin)
  130. Vietnamese
  131. Welsh
  132. Xhosa
  133. Yoruba
  134. Yucatec Maya
  135. Zulu

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. [26]

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. [27]

See also

Related Research Articles

<span class="mw-page-title-main">MSN</span> Collection of Internet sites

MSN is an American web portal and related collection of Internet services and apps for Windows and mobile devices, provided by Microsoft and launched on August 24, 1995, alongside the release of Windows 95.

<span class="mw-page-title-main">Google Translate</span> Multilingual neural machine translation service

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. As of 2022, Google Translate supports 133 languages at various levels; it claimed over 500 million total users as of April 2016, with more than 100 billion words translated daily, after the company stated in May 2013 that it served over 200 million people daily.

<span class="mw-page-title-main">Bing Mobile</span> Web search for mobile devices

Bing for mobile is a search tool for handheld mobile devices from Microsoft as part of their Bing search engine. It is designed for mobile device displays. Bing Mobile is built into Windows Mobile and Windows Phone as proprietary software, accessed via the Search key on Windows Phone 7 and Windows Phone 8 devices. It is also available on Windows Phone 8.1, and can be downloaded for other platforms, including and Android.

The Klingon scripts are fictional alphabetic scripts used in the Star Trek movies and television shows to write the Klingon language.

Microsoft engineering groups are the operating divisions of Microsoft. Starting in April 2002, Microsoft organised itself into seven groups, each an independent financial entity. In September 2005, Microsoft announced a reorganization of its then seven groups into three. In July 2013, Microsoft announced another reorganization into five engineering groups and six corporate affairs groups. A year later, in June 2015, Microsoft reformed into three engineering groups. In September 2016, a new group was created to focus on artificial intelligence and research. On March 29, 2018, a new structure merged all of these into three.

<span class="mw-page-title-main">Text Services Framework</span> Software framework and API for input method in Microsoft Windows

The Text Services Framework (TSF) is a COM framework and API in Windows XP and later Windows operating systems that supports advanced text input and text processing. The Language Bar is the core user interface for Text Services Framework.

Machine translation is an algorithm which attempts to translate text or speech from one natural language to another.

<span class="mw-page-title-main">Microsoft Azure</span> Cloud computing platform by Microsoft

Microsoft Azure, often referred to as Azure, is a cloud computing platform run by Microsoft. It offers access, management, and the development of applications and services through global data centers. It also provides a range of capabilities, including software as a service (SaaS), platform as a service (PaaS), and infrastructure as a service (IaaS). Microsoft Azure supports many programming languages, tools, and frameworks, including Microsoft-specific and third-party software and systems.

Trados Studio is a computer-assisted translation software tool which offers a complete, centralized translation environment for editing, reviewing and managing translation projects and terminology. It is available both as a local desktop tool or online. Trados, owned by RWS, also provides a suite of intelligent machine translation products.

Ultralingua is a single-click and drag-and-drop multilingual translation dictionary, thesaurus, and language reference utility. The full suite of Ultralingua language tools is available free online without the need for download and installation. As well as its online products, the developer offers premium downloadable language software with extended features and content for Macintosh and Windows computer platforms, smartphones, and other hand held devices.

<span class="mw-page-title-main">Windows Phone 7</span> First generation of Microsofts Windows Phone mobile operating system

Windows Phone 7 is the first release of the Windows Phone mobile client operating system, released worldwide on October 21, 2010, and in the United States on November 8, 2010. It runs on the Windows CE 6.0 kernel.

memoQ is a proprietary computer-assisted translation software suite which runs on Microsoft Windows operating systems. It is developed by the Hungarian software company memoQ Fordítástechnológiai Zrt., formerly Kilgray, a provider of translation management software established in 2004 and cited as one of the fastest-growing companies in the translation technology sector in 2012, and 2013. memoQ provides translation memory, terminology, machine translation integration and reference information management in desktop, client/server and web application environments.

<span class="mw-page-title-main">Cortana (virtual assistant)</span> Discontinued personal assistant by Microsoft

Cortana is a discontinued virtual assistant developed by Microsoft that used the Bing search engine to perform tasks such as setting reminders and answering questions for users.

Skype Translator is a speech to speech translation application developed by Skype, which has operated as a division of Microsoft since 2018. Skype Translator Preview has been publicly available since December 15, 2015. Skype Translator is available as a standalone app and, as of October 2015, is integrated into the Skype for Windows desktop app.

<span class="mw-page-title-main">Yandex Translate</span> Translation web service by Yandex

Yandex Translate is a web service provided by Yandex, intended for the translation of web pages into another language.

Microsoft, a technology company historically known for its opposition to the open source software paradigm, turned to embrace the approach in the 2010s. From the 1970s through 2000s under CEOs Bill Gates and Steve Ballmer, Microsoft viewed the community creation and sharing of communal code, later to be known as free and open source software, as a threat to its business, and both executives spoke negatively against it. In the 2010s, as the industry turned towards cloud, embedded, and mobile computing—technologies powered by open source advances—CEO Satya Nadella led Microsoft towards open source adoption although Microsoft's traditional Windows business continued to grow throughout this period generating revenues of 26.8 billion in the third quarter of 2018, while Microsoft's Azure cloud revenues nearly doubled.

<span class="mw-page-title-main">DeepL Translator</span> Multilingual neural machine translation service

DeepL Translator is a neural machine translation service that was launched in August 2017 and is owned by Cologne-based DeepL SE. The translating system was first developed within Linguee and launched as entity DeepL. It initially offered translations between seven European languages and has since gradually expanded to support 32 languages.

<span class="mw-page-title-main">Windows App SDK</span> Software development kit from Microsoft

Windows App SDK is a software development kit (SDK) from Microsoft that provides a unified set of APIs and components that can be used to develop desktop applications for both Windows 11 and Windows 10 version 1809 and later. The purpose of this project is to offer a decoupled implementation of capabilities which were previously tightly-coupled to the UWP app model. Windows App SDK allows native Win32 (USER32/GDI32) or .NET (WPF/WinForms) developers alike a path forward to enhance their apps with modern features.

References

  1. Carmen., Steiner (2000). Pilotstudie: über die Funktion des Anhebens der Augenbrauen in der Deutschschweizerischen Gebärdensprache DSGS. Verein zur Unterstützung der Gebärdensprache der Gehörlosen. OCLC   81702109.
  2. 1 2 "Azure Data Marketplace- Microsoft Translator". Archived from the original on 2018-02-06. Retrieved 2014-12-08.
  3. 1 2 "Microsoft Translator- Languages". Microsoft . Retrieved January 6, 2023.
  4. "Microsoft Research- Arul Menezes".
  5. 1 2 "Microsoft Research- Machine Translation".
  6. "Microsoft Translator brings end-to-end speech translation to everyone with the world's first Speech Translation API".
  7. "Microsoft Translator- Translator Text API". Microsoft . Archived from the original on 2019-09-02.
  8. "What is neural network based translation?". Archived from the original on 2021-02-08. Retrieved 2016-11-28.
  9. "A Discriminative Framework for Bilingual Word Alignment" (PDF). Archived from the original (PDF) on 2008-07-20.
  10. "Using Word Dependent Transition Models in HMM based Word Alignment for Statistical Machine Translation" (PDF).
  11. "Microsoft Translator Hub: Discussion of BLEU Score". 23 May 2013.
  12. "Microsoft Translator launching Neural Network based translations for all its speech languages". 16 November 2016.
  13. "Microsoft Translator- Products". Microsoft .
  14. "Microsoft Translator- Customization". Microsoft .
  15. "Microsoft Translator live feature". Microsoft . 18 July 2023.
  16. "Microsoft Translator- Translator Hub". Microsoft .
  17. "Where Language Meets the World: Microsoft Translator Hub". YouTube . Archived from the original on 2021-12-20.
  18. "Microsoft Translator- Multilingual App Toolkit". Microsoft .
  19. Antoniou, Grigoris; Grobelnik, Marko; Simperl, Elena; Parsia, Bijan; Plexousakis, Dimitris; de Leenheer, Pieter; Pan, Jeff Z. (2011). The Semantic Web: Research and Applications. Berlin: Springer Science+Business Media. p. 341. ISBN   9783642210334.
  20. "Translation powered by....Microsoft Translator!". Microsoft Translator (and Bing Translator) Official Team Blog. Microsoft Corporation. 8 September 2008. Retrieved 21 October 2010.
  21. 1 2 "About Bing Translator". Bing Translator. Microsoft . Retrieved 20 December 2014.
  22. "Microsoft Translator- Products". Microsoft .
  23. "Microsoft Translator- Collaborative Translation Framework". Microsoft . Archived from the original on 30 March 2015.
  24. "Microsoft Translator- Translator Web Widget". Microsoft .
  25. "Translator Language Codes". 18 July 2023.
  26. "Translator Community Partners". Microsoft .
  27. "New Bing Translator Option Lets You Translate... Klingon". 14 May 2013.

SW development