Back on May 3, I wrote about an IBM project to build a system that can play Jeopardy!. The Technology Review, published by MIT, now has an article that describes the system, called Watson, in a little more depth:
The company has not yet published any research papers describing how its system will tackle Jeopardy!-style questions. But David Ferrucci, the IBM computer scientist leading the effort, explains that the system breaks a question into pieces, searches its own databases for “related knowledge,” and then finally makes connections to assemble a result.
The key problem here is to make the system able to “understand” a Jeopardy! clue expressed in natural language.
Ferrucci describes how the technology would handle the following Jeopardy!-style question: “It’s the opera mentioned in the lyrics of a 1970 number-one hit by Smokey Robinson and the Miracles.”
The Watson engine uses natural-language processing techniques to break the question into structural components. In this case, the pieces include 1) an opera; 2) the opera is mentioned in a song; 3) the song was a hit in 1970; and 4) the hit was by Smokey Robinson and the Miracles.
The plan is to stage a match between the Watson system and human contestants, with the clues being given to the system in text format (so it doesn’t also have to deal with the problem of interpreting speech):
Demonstrations of the system are expected this year, with a final televised matchup–complete with hosting by the show’s Alex Trebek–sometime next year.
Regardless of who wins the match, this should be a fascinating exercise.