Microsoft Azure Cognitive Services Translator now supports 13 new African languages, allowing text and documents to be translated to and from these languages across the entire Microsoft ecosystem of products and services.
chiShona, Hausa, Igbo, Kinyarwanda, Lingala, Luganda, Nyanja, Rundi, Sesotho, Sesotho sa Leboa, Setswana, Xhosa, and Yoruba are the latest African languages to be supported, following the release of Somali and Zulu last year. This brings the total number of supported languages to 124, allowing millions of people in Africa and around the world to communicate in their native language.
“It is transformative when we can empower our communities across the continent to do and achieve more, and even more so, when they can do it in their own language. “We continue to build meaningful cognitive products and services that improve accessibility and break down language barriers between people and cultures all over the world,” says Wael Elkabbany, General Manager, Microsoft Africa Regional Cluster.
“The addition of new African languages enables more people and businesses to connect across languages, and language will become a seamless feature of using technology,” he adds.
Microsoft 365 for translating text and documents, the Microsoft Edge browser and Bing search engine for translating entire webpages, SwiftKey for translating messages, LinkedIn for translating user-submitted content, and the Translator app for having multilingual conversations on the go are just a few examples.
People and organizations can use Translator to add text translations for African languages to 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 while preserving their original formatting. They can also combine Translator with Cognitive Services like Speech or Computer Vision to add features like speech-to-text and image translation to their apps. With live captioning and cross-language understanding, educators can create a more inclusive classroom for both students and parents.
Microsoft has added new languages and dialects to its Translator service on a regular basis, while also ensuring the translation quality of the supported languages by employing cutting-edge neural machine translation (NMT) techniques. The company developed machine translation systems more than a decade ago through its Microsoft Research unit – and has consistently built on and improved these systems and techniques, adopting NMT technology as Artificial Intelligence (AI) evolved and migrating all machine translation systems to neural models to improve translation fluency and accuracy.
“We accomplish this by collaborating with partners in language communities who can assist in data collection for specific languages and who have access to human-translated texts.” Working with partners in language communities also helps to overcome the challenge of obtaining enough bilingual data to train and produce a machine translation model. “This network of partners assists in the collection of bilingual data, consultation with community members, and evaluation of the quality of the resulting machine translation models,” Elkabbany adds.
These ever-improving capabilities enable businesses to expand their global reach by communicating with customers and partners in multiple languages and localizing content and apps quickly, reliably, and affordably.
As part of Microsoft’s mission to build meaningful cognitive products and services that improve accessibility and local engagement, there are plans to add more of the continent’s most widely spoken languages.