Microsoft office translation

Learn more about how to use document translation in the document translation documentation. Please post your questions on Stack Overflow and add a tag [Microsoft-Translator]. This service is part of Microsoft Cognitive Services. Document Translation. Why use document translation? Translate large documents and batches of documents. Translate entire documents: Create a translated copy of documents with links intact by clicking the Review tab, and the Translate button.

You can access these documents anytime, anywhere, on all of your internet-connected devices. Using the Translator add-in for Word , you can translate selected text into any of the Microsoft Translator supported languages through a secure SSL connection.

This service is part of Microsoft Cognitive Services. How it works. Translation The text is then translated into any of the languages and dialects supported by Translator. Translations using the speech translation API as a developer or in a speech translation app or service, is powered with the newest neural-network based translations for all the speech-input supported languages see here for the full list. These models were also built by expanding the current, mostly written-text trained translation models, with more spoken-text corpora to build a better model for spoken conversation types of translations.

For any languages not supported by neural translation, traditional SMT translation is performed. Text to Speech If the target language is one of the 18 supported text-to-speech languages , and the use case requires an audio output, the text is then converted into speech output using speech synthesis. This stage is omitted in speech-to-text translation scenarios. View all publications. This service is part of Microsoft Cognitive Services. Machine Translation.

Contents What is machine translation? What is Translator? Research What is machine translation? What is machine translation? Both SMT and NMT translation technologies have two elements in common: Both require large amounts of pre-human translated content up to millions of translated sentences to train the systems. Neither act as bilingual dictionaries, translating words based on a list of potential translations, but translate based on the context of the word that is used in a sentence. How does text translation work?

Statistical machine translation. The steps neural network translations go through are the following:. Once all words have been encoded one time into these dimension vectors, the process is repeated several times, each layer allowing better fine-tuning of this dimension representation of the word within the context of the full sentence contrary to SMT technology that can only take into consideration a 3 to 5 words window The final output matrix is then used by the attention layer i.

It will also use these calculations to potentially drop unnecessary words in the target language.