Tag: Microsoft Translator

Making Teams for iOS & Android mobile devices the best tool for multi-lingual collaboration with intelligent chat message translation.

Effective collaboration and communication in a chat requires tools and features that understand who you are, where and how you like to communicate. Microsoft Teams on mobile devices can understand customers’ preferred languages and how customers like to interact with their contacts. When collaborators are chatting in different languages, the intelligent message translation feature uses their account preferences to inform the user when they would benefit from translation, and then personalizes chat translation behavior.

Microsoft Teams for iOS & Android mobile devices introduces intelligent message translation in chats. When a user receives a chat message in a language they don’t understand, Teams informs them with a prompt to translate the chat message into the user’s preferred language. The user can also personalize their chat translation behavior by turning on automatic translation.

How does it work?

When you receive a chat message in an unfamiliar language, Teams will prompt you with the option to translate it to your preferred language.

Tap Translate to translate the message.

Tap Never translate (language) if you don’t need translation for the language. Teams will stop showing you translations for that language and the language will be added to the Never translate list in Teams mobile. You can make edits to your language preferences in Teams by tapping your profile, select Settings, under General, select Translation. To remove a language from the Never translate list, delete it to undo the change.

The Help icon to the right of Never translate (language) allows you to provide feedback that will be used to improve language detection in Teams.

After using the translation feature a few times, Teams will prompt you with the option to turn on auto-translation to automatically translate messages to your preferred language.

This translation experience is available in the latest release of Microsoft Teams for iOS & Android mobile devices. By default, your translation language will be set to your Teams language.

If you want to change your default language:

1. Tap your profile picture in Teams.
2. Tap Settings. under General, select Translation. From there, you can customize your translation settings.
3. Teams supports translation to and from more than 100 languages.

Manage all your Teams mobile translation preferences in your profile Settings, under General, select Translation.

Today we’re adding two new languages, Basque and Galician, to the list of languages supported by Translator, a Microsoft Azure Cognitive Service. Basque and Galician are both Western European languages spoken by 750,000 and 2.4 million people respectively.

Basque is a language isolate, meaning it is not related to any other modern language. Basque is spoken in northern Spain and southern France in a region that straddles the Pyrenees Mountains. Galician is spoken in northern Portugal and western Spain. It is a Romance language that is closely related to Portuguese. Both languages are co-official languages of Spain.

Using Translator, you can translate to or from any of 100+ languages and dialects, now including Basque and Galician. As we continue to add new languages, Translator is available to help people translate in their personal lives, to help businesses expand their global reach, and is also used to help preserve at-risk and endangered languages.

Break the language barrier

The goal of Translator is to break the language barrier so that people can communicate freely in their language of choice and be understood by anyone around the globe. Whether you are a tourist travelling abroad, recently moved to a new country, or trying to email someone on the other side of the world, Translator powers the tools that help you communicate when and where you need.

The Microsoft Translator app for iOS and Android is your multifunctional personal translator. With the Microsoft Translator app, you can translate text, voice, images, and conversations. Translator for Bing is also available to translate text quickly on the web. You can use the Translator feature of the Edge browser to read webpages from around the world, you can quickly switch between languages on your mobile device with SwiftKey, and use Outlook to communicate with people via email regardless of the language they speak.

Expand the reach of your business

Translator is integrated into Microsoft products and is available as a service to help expand the reach of your business. With Microsoft 365, previously known as Office, you can instantly translate your Word documents, Excel spreadsheets, and PowerPoint presentations to make them accessible to a worldwide workforce or global customer base. You can also translate your Outlook emails to communicate around the globe.

Using Translator, a Microsoft Azure Cognitive Service you can add text translation to your apps, websites, workflows, and tools; or use Translator’s Document Translation feature to translate entire documents, or volumes of documents, in a variety of different file formats preserving their original formatting.

You can also build neural translation systems that understand the terminology used in your own business and industry with Custom Translator. The customized translation system can then be used with Text and Document Translation to seamlessly integrate into existing applications, workflows and websites.

To add additional capabilities such as speech-to-text and image translation into your apps, you can use Translator with Cognitive Services such as Speech or Computer Vision.

Preserving endangered languages

In order to train new language models, we must collect a large amount of bilingual training data. That is, materials written in the target language and another language. As many languages around the globe are dying, Translator is helping to preserve at-risk languages. We have worked with language communities across the world to collect and translate materials, and then create language systems. Through this we can ensure that these languages are recorded and preserved for generations to come.

Some of the at-risk languages that we have worked to preserve include Inuktitut, Māori, and Yucatec Maya. If your language community is interested in partnering with Microsoft to add your language to Translator and the products that are using it, and you have access to digital documents in your language and another commonly spoken language, please contact us using this form.

Today, we’re adding two new languages to Translator’s ever-growing list of languages—Somali and Zulu! Somali and Zulu text translation is available now in the Microsoft Translator apps, Office, and Translator for Bing. Using Translator, a Microsoft Azure Cognitive Service you can add Somali and Zulu text translation to your apps, websites, workflows, and tools; or use Translator’s Document Translation feature to translate entire documents, or volumes of documents, in a variety of different file formats preserving their original formatting. You can also use Translator with Cognitive Services such as Speech or Computer Vision to add additional capabilities such as speech-to-text and image translation into your apps.

The Somali language

The Somali language is spoken throughout the horn of Africa by more than 21 million people in Somalia, Somaliland, Ethiopia, Djibouti, and northern Kenya. The language is in the Cushitic branch of the Afroasiatic language family. It is related to languages such as Oromo, Afar, and Hadiyya.

Here are some useful phrases in Somali:

English	Somali
Hello	Haye
My name is…	Magacaygu waa…
I’m from…	Waxaan ahay reer…

Learn more about Somali on Bing.

The Zulu language

The Zulu language is spoken by 12 million people in South Africa and neighboring countries. The Zulu language is in the Bantu language family, related to languages such as Swahili and Xhosa.

Zulu is a home language of South Africa and is recognized as one of South Africa’s 11 official languages. The Zulu people are known for their intricate beadwork, which is used as both decoration and as a form of communication to convey information about the wearer.

Here are some useful phrases in Zulu:

English	Zulu
Hello	Sawubona
My name is…	Igama lami ngingu…
I’m from…	Ngivela e …

Lean more about Zulu on Bing.

What you can do with Microsoft Translator

At home
Translate real-time conversations, menus and street signs, websites, documents, and more using the Microsoft Translator app for iOS and Android.  Learn more

At work
Globalize your business and customer interactions with customizable text and document translation using Azure Cognitive Services Translator.  Learn more

In the classroom
Create a more inclusive classroom for both students and parents with live captioning and cross-language understanding.  Learn more

The Custom Translator journey to be on the leading edge of machine translation technology continues.

In early August 2020, we started our Custom Translator upgrade from Long Short-Term Memory (aka LSTM) based neural machine translation architecture (or V1) to our Microsoft Translator’s state-of-the-art Transformer based architecture (or V2). V2 is the same translation architecture which powers the standard uncustomized Translator API, as well as translation in Microsoft Office 365, Speech, Bing.com/translator, Edge, and more.

The August release enabled customers to use the dictionary (phrase or sentence) document type to build custom models on top of the V2 platform for a quick translation quality improvement over the V1 platform.

Today, Custom Translator completed the full V2 platform upgrade to deliver an even bigger translation quality gain than before. Customers can now build custom models with all document types (Training, Testing, Tuning, Phrase Dictionary and Sentence Dictionary) using full text documents, like Office documents, PDFs, HTML and plain text.

With this release, enterprises, small and medium sized businesses, app developers, and language service providers can build advanced custom neural translation systems that respect their defined business terminology and seamlessly integrate those systems into existing or new applications, workflows, and websites to attract customers and grow the business.

We put every new baseline language model through a rigorous human evaluation process to ensure the translation quality continues to meet high standards on generic input across all domains. However, with custom trained specialized translation systems, customers can achieve much higher adherence to the domain-specific terminology and style by training a custom translation system on previously translated, in-domain documents. These previously translated documents allow Custom Translator to learn the preferred translations in context, so Translator can apply these terms and phrases when the context calls for it, and produce a fluent translation in the target language, respecting the context-dependent grammar of the target language.

Benefits of the upgrade

We use BLEU score (a standard way in the research community) to measure the translation quality of a newly trained baseline model. A one or two BLEU point gain is a worthy achievement. The Custom Translator V2 platform upgrade will deliver significant improvements when compared to the previous V1 platform. The bar chart below depicts the translation quality BLEU score improvement for some domains and the impact of training dataset size.

Sample domains translation quality BLEU score when using standard Translator, Custom Translator V1, and Custom Translator V2.
Training dataset size in thousands (‘auto-28k’ means 28,000 parallel sentences for the automotive domain)

It is important to note that actual quality improvement is dependent upon customer data quality, training dataset size, and domain coverage.

“We’re hoping that translation through a neural network will not only boost quality and speed, but also offer advances in the evaluation of big data,” said Nikolas Meyer-Aun, Head of Quality and Supplier Management for Languages at Volkswagen AG

Custom Translator will offer FREE upgrade to V2. You can retrain one model per project in a workspace to the V2 platform at no charge. When you view a project, you should see a message if you still have free upgrade credit for that project. The offer starts today and ends on January 31, 2021. After January 31, 2021, normal training charges apply for each retraining.

You can learn more about the upgrade to version 2 in the FAQ below.

FAQ

1. What are you releasing in V2?
   We are releasing a Custom Translator platform upgrade (V2) to deliver significant translation quality improvements using Microsoft’s state-of-the-art neural machine translation architecture. The user experience remains the same as in V1. There is nothing new to learn, just better translations. For a quick refresher, please watch this Quick-Start video.
2. What is the benefit of upgrading a currently deployed model to the V2 platform?
   Significantly improved translation quality; the Custom Translator V2 platform upgrade will deliver significant improvement over standard Translator and the previous V1 platform. The bar chart above shows the translation quality BLEU scores for some common domains and the impact of training dataset size.
3. How do I use my FREE upgrade to V2 credit?
   When you view a project details, a free credit message becomes visible (see images below) and will continue to be visible until you either successfully retrain a model or the offer ends on January 31, 2021.

   

   

   

4. How do I upgrade my deployed (or undeployed) custom models to the V2 platform?
   If you have a deployed or undeployed dictionary-only model that was retrained after August 3, 2020, it has already been upgraded to the V2 platform. Otherwise, you should launch a new model training. Once the new model is successfully trained, the “Swap” button will be visible. Click “Swap” to deploy the new model. Note: “Swap” button enables no-downtime deployment. That is, all translation requests will continue to be served by the previous model until the new model is deployed and functional, then the new model will serve new translation requests and the previous model will be undeployed.
5. Can I continue to re-deploy V1 custom models after the V2 platform upgrade?
   Yes. We understand there may be reasons customers would want to continue using models trained on the V1 platform. V1 models can run on the V2 platform. In the future, V1 models will not be re-deployable. Note: Once you retrain a V1 model, the new model will be on the V2 platform. The “Model” tab will show all new (V2) and previous (V1) models.
6. I’m new to customizing translations, how do I get started using Custom Translator?
   To build a custom model, watch the Quick-Start video above and refer to the documentation on docs.microsoft.com: https://docs.microsoft.com/azure/cognitive-services/translator/custom-translator/overview

What you can do with Microsoft Custom Translator

Build custom models with your domain specific terminology and translate real-time using the Microsoft Translator API.

Use Microsoft Custom Translator with your translation solutions to help globalize your business and improve customer interactions.

For more information on Microsoft Translator solutions please visit: https://www.microsoft.com/translator/business.

Today, Microsoft Translator adds two Kurdish dialects, Northern and Central, to its list of text translation languages. Northern and Central Kurdish are available now, or will be available soon, in the Microsoft Translator app, Office, and Translator for Bing.

You can also use Azure Cognitive Services Translator in your own applications, websites, and tools to add Northern and Central Kurdish text translation to or from more than 70 languages. To translate speech into Kurdish text, or to translate Kurdish text into another language with speech output, you can use Azure Cognitive Services Speech, which combines Translator’s AI-powered translation service with Speech’s advanced speech recognition and speech synthesis. You can view the list of languages available for speech recognition and speech synthesis on the Microsoft Translator website.

Northern and Central Kurdish are the two most common forms of the Kurdish language. Northern Kurdish, also known as Kurmanji, is spoken in Turkey, Syria, northern Iraq, and northwest and northeast Iran by 15-17 million Kurds. Central Kurdish, also known as Sorani, is spoken in Iraqi Kurdistan and western Iran by an estimated 9-12 million Kurds. These two dialects make up about 75% of all Kurdish speakers¹.

Northern and Central Kurdish are generally not mutually understandable. Here are some examples of words and phrases in the two Kurdish dialects.

English	Northern Kurdish	Central Kurdish
Hello	Silav	سڵاو (Slaw)
What’s your name?	Navê te çi ye?	ناوت چییە؟ (Nawt tshya?)
Pleased to meet you	Kêfxweş im bi nas kirina te	خۆشحاڵبووم بە ناسینیت (Xoşhalbuum bi nasînit)

Learn more about the Northern and Central dialects of Kurdish on Bing.

What you can do with Microsoft Translator

At home

Translate real-time conversations, menus and street signs, websites, documents, and more using the Microsoft Translator app for Windows, iOS, Android, and the web. Learn more

At work

Globalize your business and customer interactions with text and speech translation powered by Translator and Microsoft Speech service, both members of the Azure Cognitive Services family. Learn more

In the classroom

Create a more inclusive classroom for both students and parents with live captioning and cross-language understanding. Learn more

For more information on Microsoft Translator please visit microsoft.com/translator.

—
¹ Translators Without Borders: https://translatorswithoutborders.org/wp-content/uploads/2017/07/Kurdish-Factsheet-English.pdf

Today, we are happy to announce that we have added Odia text translation to Microsoft Translator. Odia is available now, or will be available soon, in the Microsoft Translator app, Office, Translator for Bing, and through the Azure Cognitive Services Translator for businesses and developers.

Odia is spoken by 35 million people in India and across the world. It joins Bangla, Gujarati, Hindi, Kannada, Malayalam, Marathi, Punjabi, Tamil, Telugu, Urdu and English as the 12th commonly used language of the Indian subcontinent to be available in Microsoft Translator.

The Odia language (ଓଡ଼ିଆ)

Odia (pronounced oṛiā) is an Indo-European language native to Eastern India. It is the official language of the Indian state of Odisha and is also spoken in the nearby states of West Bengal, Jharkhand, Chhattisgarh, Madhya Pradesh, and Andhra Pradesh.

Odia is one of six languages of India to be granted to the status of a “Classical Language” by the Indian government, and has a history of literature stretching back over 1000 years.

Here are some (more modern) words and phrases in the Odia language.

English	Odia (ଓଡ଼ିଆ)	Pronunciation
Hello	ନମସ୍କାର	Namascāra
My name is…	ମୋର ନାମ …	Mora nāma …
Do you speak Odia?	ଆପଣ ଓଡ଼ିଆ କୁହନ୍ତି କି?	Āpaṇa ōṛiā kuhanti ki?

Learn more about Odia on Bing.

What you can do with Microsoft Translator

At home

Translate real-time conversations, menus and street signs, websites, documents, and more using the Microsoft Translator app for Windows, iOS, Android, and the web. Learn more

At work

Globalize your business and customer interactions with text and speech translation powered by Translator and Microsoft Speech service, both members of the Azure Cognitive Services family. Learn more

In the classroom

Create a more inclusive classroom for both students and parents with live captioning and cross-language understanding. Learn more

For more information on Microsoft Translator please visit microsoft.com/translator.

Today, we are releasing Custom Translator version 2. The newest version of Custom Translator boasts higher quality customized translations than version 1 and allows you to keep your training data in the region of your choice, if desired, in order to meet your corporate data security, data privacy, and regulatory requirements.

This upgrade to v2 will roll out in two phases to provide quicker translation quality improvements (in both accuracy and fluency) to our customers and enable regional data residency, with more regions to come. Today, we announce that phase one is live.

Higher quality translations

With Custom Translator v2, we continue our commitment to breaking down language barriers and preserving culture heritage with domain-specific data– one language at a time, one region at a time. Custom Translator v2 ups the quality game by upgrading to the newest version of Microsoft Translator’s state-of-the-art neural machine translation (NMT) architecture. These standard, general domain NMT models power Microsoft products such as Office 365, Speech Services, Teams, Bing.com/Translator, and more.

Many of our customers have reported seeing better translation quality when using a dynamic dictionary with Translator’s general domain models. We validated and quantified the quality improvement seen and decided to enable this feature as the first phase in Custom Translator service upgrade.

Deploying dictionary files through a Custom Translator model instead of using the dynamic dictionary feature in a Translator API call simplifies the translation process and reduces the maintenance cost. We expect more than 40% of our customers who train dictionary only models would immediately reap the quality improvement of Custom Translator v2 models.

Now you can use your own domain data in a dictionary document type to customize Translator’s general domain models in all Custom Translator supported languages, while continuing to build models with training document types on Custom Translator v1. You can view the complete language list in the Custom Translator Update in Azure.

Keep your data in your selected region

For customers who were previously blocked from using Custom Translator service because of corporate or regulatory requirements, today we are enabling regional data residency in Asia Pacific, Canada, Europe, and more US regions to meet your needs. If you select a region to create projects, your uploaded documents and trained models are kept at rest in the region you selected.

What you can do with Microsoft Custom Translator

Build custom models with your domain specific terminology and translate real-time using Translator on Azure.

Use the Custom Translator service to build translation solutions to help globalize your business and improve customer interactions.

For more information on Microsoft Translator, please visit microsoft.com/translator/business.

Translating one on one conversations just got even easier with the newest update to speech mode in Microsoft Translator for iOS. With Auto mode, there’s no more need to push the microphone button when it’s your turn to talk—just select the languages, turn on the mic, and start the conversation. The app will listen for the two languages and translate what you have said after you finish speaking. The other person can start talking right away when you’re finished and the app will translate automatically.

The Microsoft Translator app makes it easy to get your translations so that you can concentrate on the conversation, not the phone. There are two ways you can get your translations—either listen to the speech output or read the text translation on the screen.

The app’s split screen design makes reading the translated text simple. Place the phone between you and the other person. You can flip the text on the top portion of the phone so it can be read right side up from the other side.

If you are listening to the speech output, the app also has a brand-new option of slowing down the playback if the default speed is too fast.

Speech output is available in over 45 languages, text output is available in over 60 languages. View the Microsoft Translator app languages page.

The update will roll out to iOS apps over the next couple of days. If you are not seeing the update yet but would like to start using the feature right now, you can manually update your app. Auto mode is not available for Android, but it’s coming soon.

Get started with Auto mode

If you don’t already have the Microsoft Translator app, you can download it for free from the App Store. To start your translated conversation:

1. Open the app and click on the microphone icon to start speech mode.
2. Choose your two languages and select auto.
3. Press the microphone icon and start talking! You can also flip the text of one of the sides of the screen to make it easier for the other person to read.

 

Do more with the Microsoft Translator app

Multiparty Conversations – Translate conversations with up to 100 people with each participant using their own using their own device.

Text – Translate text in over 60 different languages. You can even download offline language packs so you can translate when you’re not connected to the Internet.

Camera – Translate the text in photos with the app’s built-in camera viewer, or upload saved photos from your gallery.

Phrasebooks – Get verified translations for travel, directions, lodging, dining, and more. Pronunciation guides to help you learn important phrases.

Single Microphone – Tap and speak into the microphone to translate short phrases while online.

Learn more about the Microsoft Translator app.

Learn more:

Microsoft Translator adds Marathi, Gujarati, Punjabi, Malayalam and Kannada as new languages.

मराठी भाषेचे स्वागत आहे

ગુજરાતી ભાષાનું સ્વાગત છે

ਪੰਜਾਬੀ ਭਾਸ਼ਾ ਦਾ ਸਵਾਗਤ ਹੈ

മലയാള ഭാഷയെ സ്വാഗതം

ಕನ್ನಡ ಭಾಷೆ ಸ್ವಾಗತ

Microsoft Translation team’s ongoing mission to break down language barriers continues with the addition of five languages of India: Marathi, Gujarati, Punjabi, Malayalam and Kannada. These five languages are widely used in different regions of India and around the world by a large Indian diaspora.

The Microsoft Translator team continuously improves translation quality based on technology advancements and usage signals. Neural machine translation technology has recently achieved impressive quality gains, characterized by highly fluent and accurate output. Using multilingual neural machine learning, the Translator team has leveraged data from languages belonging to the same family to build and refine these models and greatly enhance their quality. With this release, Microsoft Translator now translates ten languages of the Indian subcontinent covering 90% of commonly used languages in India.

These languages are available now on all Microsoft Translator apps, add-ins, Bing Translator, Microsoft Office and through the Azure Cognitive Services Translator API for businesses and developers. They will also be rolled out to the new Microsoft Edge browser and other Microsoft products in the coming days.

Details about these languages

Marathi (pronounced məˈrati) is an Indo-Aryan language spoken by approximately 83 million people in the Indian state of Maharashtra. The language has some of the oldest literature of all modern Indian languages, dating from around 600 AD, written in Devanagari script. The release of this languages happens to coincide closely with formation day of the state of Maharashtra, which is the 1^st of May. Find out more about Marathi here.

Gujarati (pronouncedˌɡuːdʒəˈrɑːti) is an Indo-Aryan language spoken by approximately 55 million people in the Indian state of Gujarat. It is the official language in the state, as well as in the neighboring territories of Dadra, Nagar Haveli, Daman and Diu. The Gujarati language uses the Abugida script. The release of Gujarati also happens to coincide closely with the formation day of the state of Gujarat as well, which is also the 1^st of May. Find out more about Gujarati here.

Punjabi (pronounced pʌnˈdʒɑːbi) is an Indo-Aryan language with more than 33 million native speakers in the Indian subcontinent and around the world. It is the predominant language in the Indian state of Punjab. Our machine translation is trained on content in the Gurmukhi script, which is the official script for the Punjabi language in India. We wish people of Punjab Happy and Safe Baisakhi and hope this release helps to reduce communication  barriers. Find out more about Punjabi here.

Malayalam (pronounced muh·lyaa·luhm) is a Dravidian language spoken by approximately 37 million people in the Indian state of Kerala and the union territories of Lakshadweep and Puducherry.  Malayalam script is based on the Vatteluttu script . We wish the people of Kerala Happy and Safe Vishu and hope this release helps to reduce communication barriers. Find out more about Malayalam here.

Kannada (pronounced kanədə) is a Dravidian language spoken predominantly by the 44 million people in Indian state of Karnataka. The Kannada language is written using the Kannada script, which evolved from the 5th-century Kadamba script. Find out more about Kannada here.

What you can do with Microsoft Translator

Translate real-time conversations, menus and street signs, websites, documents and more using the Translator app for Windows, iOS, Android and the web.

Neural machine translation models for these newly supported languages are now available as part of the Microsoft Translator API, a member of the Azure Cognitive Services family. Use these services to build translation solutions to help globalize your business and improve customer interactions.

Create a more inclusive classroom for both students and parents with live captioning and cross-language understanding.

For more information on Microsoft Translator please visit: https://www.microsoft.com/translator/.