Please create an account to participate in the Slashdot moderation system

 



Forgot your password?
typodupeerror
×
IBM Entertainment Games Science

How IBM Plans To Win Jeopardy! 154

wjousts writes "Technology Review is reporting on IBM's plans to take on Trebek at his own game. The 'Watson' computer system uses natural-language processing techniques to break down questions into their structural components and then search its database for relevant answers. A televised matchup with Trebek is planned for next year. '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. Watson is not designed to search the Web, and IBM's end goal is a system that it can sell to its corporate customers who need to make large quantities of information more accessible.'"
This discussion has been archived. No new comments can be posted.

How IBM Plans To Win Jeopardy!

Comments Filter:
  • Wordplay (Score:5, Insightful)

    by ooutland ( 146624 ) on Wednesday May 27, 2009 @11:19AM (#28110085) Homepage

    A lot of Jeopardy questions are wordplay-dependent, something AI doesn't have the hang of yet (unless IBM has been toiling in secret on something truly amazing). Categories like "Rhyme Time" and questions like "Qhat does a Pharoah need when he has a cold?" (Answer: an Egyptian Prescription) are beyond the ken of a data search.

    Many Jeopardy "answers" have the key to the answer within the question, though in some cases it may be enough to throw the program off. IE in a category like "Musicals" an answer like "Unlike his other hits, this musical wasn't 'the cat's meow' on Broadway." Raw data crunching will pair musicals, Broadway and "cats" but won't know where to go with "unlike." Only an aficionado will know that Andrew Lloyd Weber's "Starlight Express" tanked on Broadway.

    So the writers, given any knowledge of the limitations of AI, can set a challenge which will be nearly impossible for current AI to meet. John Henry will live another day.

  • Alex will interject while reading the category such as "'Cats'--and that means all the words in this category start with 'Cat'."

    Then the bot would read the closed caption that the category is "CATS MEANING ALL RESPONSES HAVE A WORD THAT STARTS WITH CAT" and include that in its reasoning. Then the clue "They are the popular makers of earth moving equipment" becomes something like "They are the popular makers of earth moving equipment, starting with 'CAT'".

  • by Ethanol-fueled ( 1125189 ) * on Wednesday May 27, 2009 @11:33AM (#28110281) Homepage Journal
    It's possible that the questions for that particular show will be specifically chosen to be more explicit and less ambiguous (avoiding the show's characteristic punny wordplay) to put the machine on a more level playing field, keeping its score closer to those of the contestants', which will make the episode more exciting to watch.
  • by eldavojohn ( 898314 ) * <eldavojohn@noSpAM.gmail.com> on Wednesday May 27, 2009 @11:36AM (#28110333) Journal

    It's possible that the questions for that particular show will be specifically chosen to be more explicit and less ambiguous ...

    Yes, clues like "It's the cube root of 474552" would level the playing field.

    Isn't the purpose of this to let Jeopardy be Jeopardy? And see if a computer can compete at what the show is?

  • by Bigjeff5 ( 1143585 ) on Wednesday May 27, 2009 @12:14PM (#28110915)

    Well, we already know that, it's 42.

    The real question, is what is the real question for which 42 is the answer? That one is the tough one.

    I suggest we build a planet, who's sole purpose is to calculate that question...

He has not acquired a fortune; the fortune has acquired him. -- Bion

Working...