Why TV captions are still so terebel
Machine translation is responsible for much of today’s closed-captioning and subtitling of broadcast and online streaming video. It can’t register sarcasm, context, or word emphasis. It can’t capture the cacophonous sounds of multiple voices speaking at once, essential for understand the voice of an angry crowd of protestors or a cheering crowd. It just types what it registers.

June 23, 2014 at 9:10PM
via Digg http://ift.tt/1paGgcu