ABSTRACT
Big data comes in two forms: the structured data intended for computer processing and the unstructured language that people read, write, and speak. Unfortunately, no computer system today can reliably translate unstructured language to the structured formats of databases, spreadsheets, and the semantic web. But they can do a lot of useful processing, and they are becoming more versatile. While we are still some distance away from the talking computer, HAL, in Stanley Kubrick’s film 2001: A Space Odyssey, this entry surveys the state of the art, the cutting edge, and the future directions for natural language processing that paves the way in getting us one step closer to the reality presented in that movie.
