Natural Language Processing Can’t Beat Human Translators (Yet)

By on

2616846695_a853cabbfa_oby Angela Guess

Ofer Shoshan of Beta News recently wrote, “Anyone who has tried to read a Google Translated article knows that machine translations still don’t entirely get things like context, colloquial and nuance. This hysterical rendition of the hit song ‘Let It Go’ — where the lyrics were Google Translated into another language and translated back into English (‘Lit white snow on the mountain tonight/ no visible legs/Discrimination Law/is probably the queen….’) — makes this point crystal clear. Having your message lost in translation is often comic, but it can also be downright embarrassing. Take the case of Sajid Javid, the British Economic Secretary to the Treasury (similar to Secretary of the Treasury), whose title was quite literally translated to a visiting Japanese delegation as ‘Cheap Typist’.”

Shoshan continues, “The Skype Translator, with its advanced machine learning, will no doubt get better with time, but still has a long way to go to match the level of accuracy, creativity and flair for language of a professional human translator. So, while machine translations may be great for rudimentary translations or even video calls, professional human translators are expert craftsmen, linguists, wordsmiths and proofreaders all wrapped in one. In addition to possessing cultural insight, they also are better editors who shape and perfect a piece for better public consumption, guaranteeing a level of faithfulness to the original document — a skill that not even the most cutting-edge machine translation technology is capable of doing just yet.”

Read more here.

Image: Courtesy Flickr/ elizabethdunn

Leave a Reply