Abstract :
Much of the world´s knowledge is recorded in natural language text, but making effective use of it in this form poses a major challenge. Information extraction converts this knowledge to a structured form suitable for computer manipulation, opening up many possibilities for using it. In this review, the author describes the processing pipeline of information extraction, how the pipeline components are trained, and how this training can be made more efficient. He also describes some of the challenges that must be addressed for information extraction to become a more widely used technology.
