In a bid to make technology accessible and productive for all, Microsoft has announced the integration of Artificial Intelligence (AI) and Deep Neural Networks (DNN) to improve real-time language translation for Hindi, Bengali, and Tamil. As per Microsoft, the technology will help users in getting results that are more accurate and natural while surfing the internet across any website on the Microsoft Edge browser, on Bing search and Bing Translator website.
The new technology will also enhance the overall search and translation functionality in Microsoft Office 365 products such as Word, Excel, PowerPoint, Outlook, and Skype. Microsoft believes that the power of AI can improve the lives of people and is using AI-powered solutions to positively impact agriculture, healthcare, education, governance and more, across India.
Let's find out how Microsoft's new tools deliver improved results.
Microsoft translator is equipped with 'TrueText'- a satellite DNN based system that enhances the translation's contextual appropriateness by filtering repetition, pauses, and indifferent words. The technology is also available for Android and iOS users through Microsoft Translator app which can recognize and translate languages from text, speech and even photos. For its partners and customers, Microsoft also provides APIs on Azure that they can use in their products.
Deep Neural Networks have the capability of encoding more granular concepts like gender (feminine, masculine, neutral), politeness level (slang, casual, written, formal), and type of word (verb, noun, adjective). As per Microsoft, Deep Neural Networks-powered translation systems have shown a significant improvement in both automatic and human evaluation metrics. More specifically, there has been at least a 20% improvement in translation quality for all Indic languages currently supported by Microsoft.
Microsoft has been working on Statistical Machine Translation (SMT) to translate global as well as Indian languages from over two decades. The incorporation of Deep Neural Networks into translating complex Indian languages has been engineered to bring more accuracy and fluency to translation.
Sundar Srinivasan, General Manager - AI & Research, Microsoft India says, "We're committed to empower every Indian and every business in India by bringing the power of AI into their daily life and become a driving force for Digital India. Microsoft celebrates the diversity of languages in India and wants to make the vast internet even more accessible".
As noted, Microsoft has been keen in accelerating computing in translation for Indian languages through Project Bhasha which was launched in 1998 and has been working with Indic languages for over 20 years. The company also supports text input in all 22 constitutionally recognized Indian languages across its products, Windows interface in 12 languages, and has a dedicated portal that provides computing tools for Indic languages called Bhashaindia.com.