Today, we are super excited to announce the release of neural dictionary, a significant translation quality improvement to our platform. In this blog post, we will explore the neural dictionary feature.

Introduction  

Neural dictionary is an extension to our dynamic dictionary and phrase dictionary features in Azure AI Translator. Both allow our users to customize the translation output by providing their own translations for specific terms or phrases. Our previous method used verbatim dictionary, which was an exact find-and-replace operation. Neural dictionary improves translation quality for sentences which may include one or more term translations by letting the machine translation model adjust both the term and the context to produce more fluent translation. At the same time, it preserves the high term translation accuracy.  

The following English-German example demonstrates differences in translation outputs between both methods when a custom terminology translation is requested: 

Quality improvement 

The chart below illustrates the significant improvements the new feature brings on common publicly available terminology test sets in Automotive (https://aclanthology.org/2021.eacl-main.271), Health (https://aclanthology.org/2021.emnlp-main.477) and Covid-19 domains (https://aclanthology.org/2021.wmt-1.69) using our general translation models. 

We also conducted a series of customer evaluations on Custom Translator platform and neural dictionary models. We measured the translation quality gains on customer data between models with and without the neural dictionary extension. Five customers participated, covering German, Spanish, and French in different business domains.

The chart below shows the average improvement of COMET in the education domain for English-German, English-Spanish, and English-French; for general models on the left, and for customized models on the right. BLUE color bars represent general translation quality without neural dictionary and ORANGE color bars represent translation quality using neural dictionary. These are overall average improvements on the entire test sets. For segments including one or more customer’s dictionary entries (between 19% and 63%), the improvement is as high as +6.3 to +12.9 COMET points. 

 Supported languages  

• Currently available (as of December 6, 2023): Chinese simplified, French, German, Italian, Japanese, Korean, Polish, Russian, Spanish and Swedish – to and from English.  
• We are adding more in the future. For updates, refer to Custom Translator release notes.  

How neural dictionary works 

Neural dictionary does not employ the exact find-and-replace operation when handling custom terminology translation. Instead, it translates terms or phrases from the dictionary in a way that fits best the entire context. This means that the term can be inflected or have different casing, or that the surrounding words can be adjusted, producing a more fluent and coherent translation.  

Let’s say, for example, we have the following input sentence in English and its translation into Polish without any dictionary phrases is as follows:  

If you want to make sure that “solution” is translated as “alternatywa” (“an alternative” in English), you can add a dynamic dictionary annotation to achieve that:  

The output produced by the previous method is not fluent as grammatical gender consistency is violated. The neural dictionary produces fluent output by a) inflecting the requested replacement and b) changing the surrounding words where needed. It can also change the casing in some cases, as in the following example:  

Neural dictionary expects that the requested translation of a term is provided in its base grammatical form. Multi-word terms are also supported and should be provided as noun phrases, i.e., words should not be lemmatized independently (for example, “Estonian parliamentary election” will be better than “Estonia parliament election”). 

How to enable neural dictionary 

For all supported languages listed above, neural dictionary is immediately available for all customers using Custom Translator platform with phrase dictionaries. Full (or dictionary only) custom model retraining is required to enable neural dictionary. 

 Recommendations 

1. If you want to ensure that the phrase dictionary entry is used more often when working with neural dictionary, you may consider adding the phrase entry with the source part in various forms. In the above example, next to “solution _ alternatywa”, you may want to add the following entries as well: “Solution _ alternatywa”, “solutions _ alternatywy”, “Solutions _ alternatywy”.  
2. If the goal is to ensure that a specific word or phrase is copied “as is” from the input text to the output translation when using phrase dictionary, consider enforcing verbatim dictionary as it may be more consistent.   
3. Avoid adding translations of common or frequent words or phrases to the phrase dictionary.  

To learn more about Custom Translator and how it can help your business thrive in the global marketplace, start with the Custom Translator beginner’s guide. 

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, visit Microsoft Translator business solutions and Custom Translator release notes. 

The post Azure AI Custom Translator Neural Dictionary: Delivering Higher Terminology Translation Quality  appeared first on Microsoft Translator Blog.

As businesses increasingly look to expand their global reach, the demand for high-quality, accurate translations has never been higher. At Microsoft, we’re committed to providing the most powerful and effective translation tools available, and we’re excited to announce the latest upgrade to our Custom Translator platform.

In recent years, Custom Translator was upgraded to state-of-the-art Transformer architecture as part of our ongoing effort to improve our custom translation and provide the best possible translation quality to our customers. The upgrade was done in two phases, first phase was completed in November 2020 and second phase was completed in August 2022.

And today, we unveiled a significant upgrade to our platform. In this blog post, we will explore the model quality trained on the new Custom Translator platform.

Custom Translator platform’s latest upgrade is still based on the Transformer architecture; however, our team of experts have been hard at work developing a new set of algorithms and techniques, grounded by customer feedback and testing, to improve the accuracy and quality of Custom Translator models when adapted to customer terminology and domain data. Thanks to these enhancements, customers can now expect more accurate translations than previous models.

To put it to the test, we conducted a series of customer evaluations on Custom Translator’s upgraded models. Five customers participated, covering German, Spanish, French, Japanese and Chinese in different business domains. The results were impressive, with significant improvements in translation quality.

The chart below shows the average improvement from the customer evaluations.

The blue solid bars show the average improvement across language pairs when comparing our strong general models to the new Custom Translator platform adapted to the customer domain terminology and data. Across the five customers and five languages, there is a 4.3 BLEU improvement of the custom models over our strongest general models. For customers with parallel data, using Custom Translator provides even higher quality translation than our general systems.

The striped green bars show the average improvement across language pairs when comparing the new Custom Translator system adapted to the customer data to the previous version of Custom Translator. Across the five customers and five languages, there is a 4.5 BLEU improvement. For customers already using Custom Translator, the new platform upgrade provides an even larger improvement.

We’re thrilled to offer this upgrade to customers and we’re confident it will help businesses around the world communicate more effectively and efficiently. Custom Translator is now even more powerful and effective than ever before.

To learn more about Custom Translator and how it can help your business thrive in the global marketplace, start with the Custom Translator beginner’s guide.

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, visit Microsoft Translator business solutions and Custom Translator release notes.

The post Microsoft Custom Translator Platform Upgrade: Delivering Higher Custom Translation Quality appeared first on Microsoft Translator Blog.

Today, we are introducing a new language to the ever-growing list of Translator languages – welcome Lower Sorbian! 

Adding Lower Sorbian to Translator was made possible by the Sorbian language community, in particular the Foundation for the Sorbian People, the Sorbian Institute and the Witaj Language Centre  which donated data to create the new language system, following up on our collaboration to build language support for Upper Sorbian last year. 

Beate Brězan, Head of the WITAJ Language Centre, states that “the addition of Lower Sorbian to Microsoft Translator is a valuable contribution to the preservation of our cultural identity. The ability to translate between Sorbian and more than 100 languages enables our speech community to write in our own language and be understood by others, and vice-versa.” 

Bernd Melcher, Head of the WITAJ Department in Lower Lusatia, highlights the positive impact of the language’s integration into Translator: “Now we can create much-needed textbooks, study materials, and other publications at a larger scale. And our students can use their mobile devices for quick look-up of words and even save the translations – very motivating!” 

Text translation for Lower Sorbian is available now in the Microsoft Translator apps, Office, and Translator for Bing. Using Translator, a Microsoft Azure Cognitive Service, you can add Lower Sorbian 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 Vision, to add additional capabilities such as speech and image translation into your apps. 

About the Lower Sorbian language 

Lower Sorbian (dolnoserbšćina) is a West Slavic minority language spoken in eastern Germany in the historical province of Lower Lusatia, today part of Brandenburg. Signs in this region are typically bilingual, and the city of Cottbus (Chóśebuz) has a Lower Sorbian High School where one language of instruction is Lower Sorbian. It is a heavily endangered language with less than 7,000 speakers. 

 Learn more about Lower Sorbian 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 post Introducing Lower Sorbian appeared first on Microsoft Translator Blog.

Today, we are delighted to announce that we have added three new Indian languages to Microsoft Translator – Konkani, Maithili, and Sindhi. Along with this, we are also adding support for Sinhala, the official language of Sri Lanka. With this latest release, Microsoft is further democratizing access to information in native languages for India. This brings our total number of supported languages to 128 and adds language support for 16 Indian languages including Assamese, Bengali, Gujarati, Hindi, Kannada, Konkani, Maithili, Malayalam, Marathi, Nepali, Odia, Punjabi, Sindhi, Tamil, Telugu, and Urdu. 

Text translation for the four new languages is available now in the Microsoft Translator apps, Office, and Translator for Bing. Using Translator, a Microsoft Azure Cognitive Service, you can add Indian languages’ 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 Vision, to add additional capabilities such as speech and image translation into your apps. 

About the Konkani language 

Konkani is primarily spoken by over 2 million people in the states of Goa, Maharashtra, and Karnataka. It is also spoken by a significant number of people in other parts of India, such as Kerala and Gujarat. 

 Learn more about Konkani on Bing. 

About the Maithili language 

Maithili is spoken by over 75 million people in India and Nepal. Popularly written in Devanagari script, it has its own script variously called Mithilakshara, Tirhuta, and Maithili. Maithili is mainly spoken in the northern regions of Indian state of Bihar, in parts of the state of Jharkhand and in the Terai regions of Nepal. The development of Maithili was championed by Dr. Girish Nath Jha, professor of Computational Linguistics at the School of Sanskrit & Indic Studies, Jawaharlal Nehru University (New Delhi, India), Dr. Ritu Nidhi and their team of research students.  We collaborated closely with the JNU community who helped with their expertise in machine translation and resource creation. 

 Learn more about Maithili on Bing. 

About the Sindhi language 

Sindhi is spoken by over 20 million people in Pakistan, India, and Afghanistan. 

 Learn more about Sindhi on Bing. 

About the Sinhala language 

Sinhala is spoken by over 16 million people in Sri Lanka, as well as in other countries such as Malaysia and Singapore.  

 Learn more about Sinhala 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 post Announcing four new languages: Konkani, Maithili, Sindhi and Sinhala  appeared first on Microsoft Translator Blog.

We are excited to announce the release of a new UI feature to translate documents in language studio without writing a single line of code. Enterprises can deploy this solution across their organization, enabling employees to translate documents on demand. The feature is powered by Azure Cognitive Services (ACS) Translator document translation API, which can translate documents in variety of formats preserving the original structure and format as in the source document.

Document translation experience in the language studio enables customers to easily evaluate and adopt the service by simply configuring their Azure Translator and Storage resources. Customers could scale and control the usage through Azure Active Directory (AAD) authentication.

This new experience leverages the full capabilities of the document translation service and offers more. You could translate documents from either your local system or Azure blob storage. Likewise, the translated documents could be either downloaded to your local system or stored in Azure blob storage. Optionally, you could specify the glossary or custom models to be used during translation.

Why should I use the language studio to translate documents?

• • Enterprise ready UI solution to translate documents securely.
  • Language studio does not store customer data.
  • Scale and control the usage through AAD authentication.
  • You can use your existing Azure account and translator resources.
  • Since it is a web app, you can access the feature from any operating system.

How do I use this feature?

1. 1. Sign In into the language studio using your Azure credentials.
   2. Click on ‘Document translation (Preview)’ tile.
   3. Configure your setup by choosing your Translator resource and Azure Storage account.
   4. Select source and target language(s).
   5. Choose the source document(s) from your local system or blob storage.
   6. Choose the destination for translated files as either blob storage upload or local system download.
   7. Translate!

You can monitor the status of current and previously submitted jobs through the ‘Job History’ page.

References:

• • Translator Documentation
  • Translator Pricing
  • Send your feedback to mtfb@microsoft.com

The post Document Translation now available in the Language Studio appeared first on Microsoft Translator Blog.

Today, we are excited to announce that we have added 13 new African languages to Microsoft Translator! Following last year’s release of Somali and Zulu, this release highlights our continued efforts of empowering African language communities to achieve more. Microsoft Translator now supports:

• chiShona (7 million speakers)
• Hausa (72 million speakers)
• Igbo (40 million speakers)
• Kinyarwanda (10 million speakers)
• Lingala (65 million speakers)
• Luganda (21 million speakers)
• Nyanja (1 million speakers)
• Rundi (12 million speakers)
• Sesotho (14 million speakers)
• Sesotho sa Leboa (15 million speakers)
• Setswana (13 million speakers)
• Xhosa (10 million speakers)
• Yoruba (55 million speakers)

This brings our total number of supported languages to 124 and adds language support for more than 335 million people in Africa and worldwide.

Text translation for the 13 new African languages is available now in the Microsoft Translator apps, Office, and Translator for Bing. Using Translator, a Microsoft Azure Cognitive Service, you can add African languages’ 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.

About the chiShona language

The chiShona language is spoken by 7 million people in Zimbabwe and Mozambique. The language is in the Bantu language family. Here are some useful phrases in chiShona:

Learn more about chiShona on Bing.

About the Hausa language

The Hausa language is spoken by 72 million people in Niger, Nigeria, and Benin, as well as throughout other West African countries. The language is in the Chadic branch of the Afroasiatic language family. Here are some useful phrases in Hausa:

Learn more about Hausa on Bing.

About the Igbo language

The Igbo language is spoken by 40 million people in Nigeria, Equatorial Guinea, and Cameroon. The language is in the Niger-Congo language family. Here are some useful phrases in Igbo:

Learn more about Igbo on Bing.

About the Kinyarwanda language

The Kinyarwanda language is spoken by 10 million people in Rwanda, Uganda, DR Congo, and Tanzania. The language is in the Bantu language family. It is officially known as Ikinyarwanda. Here are some useful phrases in Kinyarwanda:

Learn more about Kinyarwanda on Bing.

About the Lingala language

The Lingala language is spoken by 65 million people in DR Congo and the Republic of the Congo. The language is in the Bantu language family. Here are some useful phrases in Lingala:

Learn more about Lingala on Bing.

About the Luganda language

The Luganda language is spoken by 21 million people in Uganda. The language is in the Bantu language family. Here are some useful phrases in Luganda:

Learn more about Luganda on Bing.

About the Nyanja language

The Nyanja language is spoken by 1 million speakers in Malawi, Mozambique, and Zambia. The language is in the Bantu language family. It is also known as Chewa. Here are some useful phrases in Nyanja:

Learn more about Nyanja on Bing.

About the Rundi language

The Rundi language is spoken by 12 million speakers in Burundi, Rwanda, Tanzania, DR Congo, Uganda, and Kenya. The languages is in the Bantu family of languages. Here are some useful phrases in Rundi:

Learn more about Rundi on Bing.

About the Sesotho language

The Sesotho language is spoken by 14 million speakers in Lesotho, South Africa, and Zimbabwe. The language is in the Bantu family of languages. It is also known as Sotho or Souther Sotho. Here are some useful phrases in Sesotho:

Learn more about Sesotho on Bing.

About the Sesotho sa Leboa language

The Sesotho sa Leboa language is spoken by 15 million speakers in South Africa. The language is in the Bantu family of languages. It is also known as Northern Sotho or Sepedi. Here are some useful phrases in Sesotho sa Leboa:

Learn more about Sesotho sa Leboa on Bing.

About the Setswana language

The Setswana language is spoken by 13 million people in Botswana, South Africa, Zimbabwe, and Namibia. Here are some useful phrases in Setswana:

Learn more about Setswana on Bing.

About the Xhosa language

The Xhosa language is spoken by 10 million people in South Africa, Zimbabwe, and Botswana. It is in the Bantu family of languages. Here are some useful phrases in Xhosa:

Learn more about Xhosa on Bing.

About the Yoruba language

The Yoruba language is spoken by 55 million people in Nigeria, Benin, and Togo. Here are some useful phrases in Yoruba:

Learn more about Yoruba 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 post Introducing 13 New African Languages appeared first on Microsoft Translator Blog.

We’re excited to announce that, as of today, masculine and feminine alternative translations are available for when translating from English to Spanish, French, or Italian. You can try out this new feature in both Bing Search and Bing Translator verticals.

Over the last few years, the field of Machine Translation (MT) has been revolutionized by the advent of transformer models, leading to tremendous improvements in quality. However, models optimized to capture the statistical properties of data collected from the real world inadvertently learn or even amplify social biases found in that data.

Our latest release is a step towards reducing one of these biases, specifically gender bias that is prevalent in MT systems. Bing Translator has always produced a single translation for an input sentence even when the translations could have had other gender variations including feminine and masculine variants. In accordance with the Microsoft responsible AI principles, we want to ensure we provide correct alternative translations and are more inclusive to all genders. As part of this journey our first step is to provide feminine and masculine translation variants.

Gender is expressed differently across different languages. For example, in English, the word lawyer could refer to either a male or female individual, but in Spanish, abogada would refer to a female lawyer, while abogado would refer to a male one. In the absence of information about the gender of a noun like ‘lawyer’ in a source sentence, MT models may resort to selecting an arbitrary gender for the noun in the target language. Often, these arbitrary gender assignments align with stereotypes, perpetuating harmful societal bias (Stanovsky et al., 2019; Ciora et al., 2021) and leading to translations that are not fully accurate.

In the example below, you notice that while translating gender-neutral sentences from English to Spanish, the translated text follows the stereotypical gender role, i.e., lawyer is translated as being male.

As there is no context in the source sentence that implies the gender of the lawyer, producing a translation with the assumption of either a male or female lawyer would both be valid. Now, Bing Translator produces translations with both feminine and masculine forms.

System design

We aimed to design our system to meet the following key criteria for providing gendered alternatives:

1. The feminine and masculine variants should have minimal differences except for those needed to convey gender.
2. We wanted to cover a wide range of sentences where multiple gendered alternatives are possible.
3. We wanted to ensure that the translations preserve the meaning of the original source sentence.

Detecting gender ambiguity

In order to accurately detect gender ambiguity in source text, we utilize a coreference model to analyze inputs containing animate nouns. For instance, if a given input text contains a gender-neutral profession word, we only want provide gendered alternatives for it when its gender can’t be determined by other information in the sentence. For example: On translating an English sentence “The lawyer met her driver at the hotel lobby.” into French we can determine that the lawyer is female, while the gender of the driver is unknown.

Generating alternate translation

When the source sentence is ambiguously gendered, we examine our translation system’s output to decide if an alternative gender interpretation is possible. If so, we proceed to determine the best way to revise the translation. We begin by constructing a set of candidate target translations by rewriting the original translation. We apply linguistic constraints based on dependency relations to ensure consistency in the proposed alternatives and prune the erroneous candidates.

However, in many cases, even after applying our constraints, we are left with multiple candidate rewrites for the gendered alternative translation. To determine the best option, we evaluate each candidate by scoring it with our translation model. By leveraging the fact that a good gender rewrite will also be an accurate translation of the source sentence, we are able to ensure high accuracy in our final output.

Leveraging managed online endpoints in Azure Machine Learning

The gendered alternative feature in Bing is hosted on managed online endpoints in Azure Machine Learning. Managed online endpoints provide a unified interface to invoke and manage model deployments on Microsoft-managed compute in a turnkey manner. They enable us to take advantage of scalable and reliable endpoints without being concerned about infrastructure management. This inference environment also enables the processing of large numbers of requests with low latency. Our ability to create and deploy the gender debias service with the latest frameworks and technologies has been greatly improved through the use of managed inference features in Azure Machine Learning. By leveraging these features, we have been able to maintain low COGS (Cost of Goods Sold) and ensure straightforward security and privacy compliance.

How can you contribute?

To facilitate progress in gender bias reduction in MT, we are releasing a test corpus containing gender-ambiguous translation examples from English into Spanish, French and Italian. Each English source sentence is accompanied by multiple translations, covering each possible gender variation.

Our test set is constructed to be challenging, morphologically rich and linguistically diverse. This corpus has been instrumental in our development process. It was developed with the help of a bilingual linguists with significant translation experience. We are also releasing a technical paper that discusses the test corpus in detail and the methodology and tools for evaluation.

GATE: A challenge set for Gender-Ambiguous Translation Examples – Paper

GATE: A challenge set for Gender-Ambiguous Translation Examples – Test set

Path forward

Through this work we aim to improve the quality of MT output in cases of ambiguous source gender, as well as facilitate the development of better and more inclusive natural language processing (NLP) tools in general. Our initial release focuses on translating from English to Spanish, French, and Italian. Going forward, we plan to expand to new language pairs, as well as cover additional scenarios and types of biases.

Credits:

Ranjita Naik, Spencer Rarrick, Sundar Poudel, Varun Mathur, Jeshwanth Kumar Chandrala, Charan Mohan, Lee Schwartz, Steven Nguyen, Amit Bhagwat, Vishal Chowdhary.

The post Bing’s gendered translations tackle bias in translation appeared first on Microsoft Translator Blog.

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.

The post Announcing intelligent message translation in Microsoft Teams for mobile devices appeared first on Microsoft Translator Blog.

Using Microsoft Speech Translation technology powered by Azure Cognitive Services, live translation for captions in Teams supports 40 spoken languages. Live translation for captions is ideal in meetings with multi-lingual users and audiences as it supports one spoken language and multiple displayed text (subtitle) languages. Adding translation to live captions allows for more engaging, inclusive, and productive meetings.

Live translation for captions is temporarily available as a preview for all Microsoft Teams customers. After the preview period, to use live translation for captions, meeting organizers will need the Teams Premium offering. Learn more about Microsoft Teams Premium here.

The post Announcing live translation for captions in Microsoft Teams appeared first on Microsoft Translator Blog.

Today, the Document translation feature of Translator, a Microsoft Azure Cognitive Service, adds the ability to translate PDF documents containing scanned image content, eliminating the need for customers to preprocess them through an OCR engine before translation.

Document translation was made generally available last year, May 25, 2021, allowing customers to translate entire documents and batches of documents into more than 110 languages and dialects while preserving the layout and formatting of the original file. Document translation supports a variety of file types, including Word, PowerPoint and PDF, and customers can use either pre-built or custom machine translation models. Document translation is enterprise-ready with Azure Active Directory authentication, providing secured access between the service and storage through Managed Identity.

Translating PDFs with scanned image content is a highly requested feature from Document translation customers. Customers find it difficult to segregate PDF documents which have regular text or scanned image content through automation. This creates workflow issues as customers have to route PDF documents with scanned image content first to an OCR engine before sending them to document translation.

Document translation services now have the intelligence

• to identify whether the PDF document contains scanned image content or not,
• to route PDFs containing scanned image content to an OCR engine internally to extract text,
• to reconstruct the translated content as regular text PDF while retaining the original layout and structure.

Font formatting like bold, italics, underline, highlights, etc. are not retained for scanned PDF content as OCR technology does not currently capture them. However, font formatting is preserved while translating regular text PDF documents.

Document translation currently supports PDF documents containing scanned image content from 68 source languages into 87 target languages. Support for additional source and target languages will be added in due course.

Now it’s easier for customers to send all PDF documents to Document translation directly and let it decide when and how to use the OCR engine efficiently.

For customers already using Document translation, no code change is required to be able to use this new feature. PDF documents with scanned content can be submitted for translation like any other supported document formats.

We are also pleased to announce that the Document translation adds support for scanned PDF document content with no additional charges to customers. Two pricing plans are available for Document translation through Azure — the Pay-as-you-go plan and the D3 volume discount plan for higher volumes of document translation. Pricing details can be found at aka.ms/TranslatorPricing.

Learn how to get started with Document translation at aka.ms/DocumentTranslationDocs.
Send your feedback to mtfb@microsoft.com.

The post Translate scanned PDF documents with Document translation appeared first on Microsoft Translator Blog.