Microsoft Translator adds Korean as the 11th Neural Network translation language

Microsoft last year announced the availability of neural network-based translation system for 10 languages: Arabic, Chinese, English, French, German, Italian, Japanese, Portuguese, Russian, and Spanish. Today, they are adding the Korean language to the list. Because of how neural networks functions, they better capture the context of full sentences before translating them, providing much higher quality and more human-sounding output. Microsoft gave the below example to highlight the advantages of using neural networks for translation systems.

M277dw? ?? ??? ????, ?????? ?? ??? ?? ? ?? ??? ????? ?? ??? ? ??.

Traditional Statistical Machine Translation would offer this translation:

“M277dw, point to the document, the paper off the file scan command Smartphone smartphones can store immediately.”

Neural Network translation, in comparison, generates this clear and fluent sentence:

“You can place a paper document on M277DW, and then save the file to your smartphone immediately after the scan command.”

You can try it out yourself here. Learn more about neural network-based translation system here.