The latest Microsoft Translator API update brings four new levels of customization, which permit companies to tailor the system to their own needs.
Microsoft´s Translator team announced today that the main reason behind the customization update is to cater to the different needs of companies. In the past, there were only two solutions for translating content – using translation websites and apps, or building a customized translation system with manually translated text.
The company has integrated its very own artificial intelligence technology and research into the Microsoft Translator Hub, which has now evolved into a more flexible translation API.
The first level of customization enables the user to select the category of text and convey Microsoft Translator what kind of translation it is.
Another customization option adds the ability to integrate a custom dictionary into Microsoft Translator, enabling you to insert “your own foreign language word lists so that the terminology that is unique to your business or industry will translate just the way you want”.
Adding text that has already been translated to the API is the third customization level, which enables you to train the system with 1,000 – 5,000 parallel sentences (pre-translated sentences in the original and custom language). By providing the Microsoft Translation Hub with such parallel sentences, you can create a better tone than standard categories and improve your translations.
Taking translation and AI self-learning to a new level, Microsoft Translator API comes with the ability to train a system with more than 5,000 parallel sentences. Such a system could itself be used to translate documents in the right tone, with correct phrases and the context of speech.
In a blog post, Microsoft emphasizes in detail all the new opportunities the new API and its translator hub is offering.
“With more than 50,000 parallel sentences, ideally in the 100s of thousands of sentences, the Hub enables you to create brand new language systems. Many of the Microsoft Translator supported languages were developed by Community Partners including the languages Hmong Daw, Yucatec Maya, Queretaro Otomi, Welsh, and Kiswahili.”