Computers aren't really known for their way with words, but that could be about to change. An artificial intelligence program recently scored as high as a 4-year-old on a test of verbal IQ. The result may help AIs develop common sense.
AIs such as Google's search engine or IBM's Watson typically perform well in specific areas, like ranking web pages or answering game-show style questions. But these systems tend to fail when asked to do things outside of their narrow area of expertise. For years researchers have attempted to build systems with a more general "common sense" understanding, but have had mixed results.
Step forward ConceptNet. Developed by Catherine Havasi and her team at the MIT Media Lab ConceptNet draws upon a crowdsourced database of millions of statements describing simple relationships between everyday objects, such as "a fawn is a deer" or "ice cream is capable of melting".
Havasi describes the system as containing "the kind of information that everybody knows about the world but that nobody ever writes down because we learn it too early".
To test ConceptNet's overall intelligence, Robert Sloan and Stellan Ohlsson of the University of Illinois at Chicago, who were not involved in the system's creation, used a standard measure of child IQ called the Wechsler Preschool and Primary Scale of Intelligence. The verbal portion of the test asks questions in five categories, ranging from simple vocabulary questions, like "What is a house?", to guessing an object from a number of clues such as "You can see through it. It is a square and can be opened. What is it?"
To answer a question from the test, like "What do you wear on your head?", ConceptNet searches its database for the object that is most closely related to the pair "wear" and "head".
For the three main categories of questions – information, vocabulary and word reasoning – Sloan and Ohlsson found that the system's aggregate verbal IQ was equal to that of an average human 4-year-old. "I didn't expect to see 4-year-old performance," says Sloan, who presented the results at the Association for the Advancement of Artificial Intelligence conference in Bellevue, Washington, last week. Havasi points out that this research only tested the system's verbal ability and ignored parts of the test that covered spatial and symbolic reasoning.
If you would like to reuse any content from New Scientist, either in print or online, please contact the syndication department first for permission. New Scientist does not own rights to photos, but there are a variety of licensing options available for use of articles and graphics we own the copyright to.
Have your say
Only subscribers may leave comments on this article. Please log in.
Only personal subscribers may leave comments on this article
All comments should respect the New Scientist House Rules. If you think a particular comment breaks these rules then please use the "Report" link in that comment to report it to us.
If you are having a technical problem posting a comment, please contact technical support.
