It is well known that the computers provide a great leverage while we deal with the texts. They or specifically speaking, the word processors take texts as data to give us excellent efficiency. But how does a computer make out of the ordinary language of man?

Can they really do anything at that plane? And the answer comes in affirmative. They can.

Can the computers analyze the instructions for a task quite unknown to them?

Researchers at MIT’s Computer Science and Artificial Intelligence Lab have begun designing machine-learning systems that do so. The efforts for last few years have brought surprisingly good results.

In the year 2009 the best paper award went to Regina Barzilay for a computer which generated the scripts for installing a piece of software by reviewing the instructions on MS help site. The lady this year is reported to have developed something greater. She with her students developed a machine learning system that when attached to a computer to receive the player’s manual led to the victory rate of the game from 46 to 79 percent. This means that the computers when assisted by a machine learning system can read the player to learn and to increase its efficiency. We are surely approaching to an age of artificial intelligence.

learn to play bridge,
“Games are used as a test bed for artificial-intelligence techniques simply because of their complexity,” says Branavan, who has been first author on both ACL papers. “Every action that you take in the game doesn’t have a predetermined outcome, because the game or the opponent can randomly react to what you do. So you need a technique that can handle very complex scenarios that react in potentially random ways.”

Barzilay says, game manuals have “very open text. They don’t tell you how to win. They just give you very general advice and suggestions, and you have to figure out a lot of other things on your own.” Games are “another step closer to the real world.”

“If you’d asked me beforehand if I thought we could do this yet, I’d have said no,” says a University Professor of Computer Science at Brown University. “You are building something where you have very little information about the domain, but you get clues from the domain itself.”

“it’s not completely clear to me that that’s really relevant. Who cares? The important point is that this was able to extract useful information from the manual, and that’s what we care about.”

Through this complex game called “Civilization”, the main purpose of the project supported by the National Science Foundation, was to show that computer systems that learn the meanings of words through two sided interaction with their users . The issue is a promising subject for further research. This is going to add in future wings to the functioning of robots. And then the age of artificial intelligence will start.