Language lessons for a self-taught computer

Few challenges in computing loom larger than understanding the meaning of language. One reason is that semantics, the meaning of words and phrases, hinges not only on context, but also on background knowledge that humans learn over the years.

Researchers at Carnegie Mellon University in Pittsburgh have been fine-tuning a computer system that is trying to master semantics by learning more like a human.

"For all the advances in computer science,we still don't have a computer that can learn as humans do, cumulatively, over the long term," said the team’s leader, Tom M. Mitchell,a computer scientist and chairman of the machine learning department.