Microsoft Translation AI: DNN vs. statistical

Machine translation of human languages has improved significantly in last 10 years, but it is still far from perfect. Here are very good articles explaining how this works now,
and interesting web site that compares various methods of translation for select languages.

Microsoft Translator: What is a neural network based translation?

Machine Translation - Microsoft Translator

Both SMT (Statistical Machine Translation) and
DNN (Deep Neural Network) 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."

Try and Compare - Microsoft Translator

Artificial Intelligence, powered by neural networks:
used to be about 20 languages, now only Chinese; site sometimes works

Bing Microsoft Translator

Classic "statistical" translator: about 60 languages; site works, and this is same as API

marketing pages:

Try Microsoft Translator for free:
Bing, Live conversations, Office 365 Word, Translate.ai

Translator Text API - Auto Translate | Microsoft Azure

Microsoft Translator | Conversations | Break the language barrier

API documentation:

docs: Microsoft Cognitive Services: Microsoft Translator Text API

Overview of Microsoft Translator API in Cognitive Services | Microsoft Docs

Supported languages in the Microsoft Translator API | Microsoft Docs

sample code calling Microsoft Translation API (classic):

MicrosoftTranslator/DocumentTranslator: Microsoft Document Translator

Google Neural Machine Translation - Wikipedia

Google paper:

Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation

Stanford lecture:
Machine Translation and Advanced Recurrent LSTMs and GRUs - YouTube


Alternative:
Google Translate