Computerized interaction with humans

Stanford is developing a new way computers can interact with humans. Not only has MIT been training the computer to more human interaction, Stanford associate professor of computer science and linguistics Chris Manning is developing the future of enabling computers to process human language well enough to use the information it conveys.

“The problem of the age is information overload,” said Manning, who delivered his presentation on Feb. 19 at the annual conference of the American Association for the Advancement of Science (AAAS) in San Diego. “The fundamental challenge I’m going to talk about is how we can get computers to actually understand at least a reasonable amount of what they read.”

As computers obtain more information about what’s online, they will deliver more relevant search results and will help summarize, structure, and act on information that the user cares about-making this seem like the perfect computerized best friend. Being able to communicate about almost anything, with the computer searching and able to respond to what you’re looking for, instead of browsing through articles of information not relevant to the users search.

“The state of the art is still highly incomplete,” Manning says. “We’re just not at the level of what we see in science fiction movies. But human language technology has been making enormous advances.”

Stanford linguistics professor Dan Jurafsky has been working with Manning to develop a set of tools to help computers parse sentences. Computers begin to understand sentences by recognizing parts of speech and how the sentence is structured. Essentially, computers are programmed to read a large number of sentences and then analyze the structure and elements, and keep track of what the subject of the sentence is doing.

Manning’s group has created software to sort out ambiguities in language by taking whole sentences into account when deciding what each word means. For instance, “make up” can have at least three meanings: to reconcile after a spat, to concoct a story, or to apply cosmetics. The technical solution, called “joint inference,” is to look for other words in the sentence that are statistically shown to be relevant. If the word “argument” is there, the computer will lean toward “to reconcile.”