Computers could become sarcastic or exaggerate for effect, say two Stanford researchers, who have developed a mathematical model aimed at improving natural language processing.
It could lead to machines that can better understand inference, context and social rules, they say. They’re already applying the model to studies on hyperbole, sarcasm and other aspects of language.
Assistant professors Michael Frank and Noah Goodman have created a quantitative theory of pragmatics – how language is used in social situations – that could allow computers to use language as flexibly as we do.
They signed up 745 participants, who saw a set of objects and were asked to pick which one was being referred to by a particular word.
For example, one group of participants saw a blue square, a blue circle and a red square. The question for that group was: ‘Imagine you are talking to someone and you want to refer to the middle object. Which word would you use, ‘blue’ or ‘circle’?’
The other group was asked: ‘Imagine someone is talking to you and uses the word ‘blue’ to refer to one of these objects. Which object are they talking about?’
The results allowed Frank and Goodman to create a mathematical equation to predict human behavior and determine the likelihood of referring to a particular object.
“Before, you couldn’t take these informal theories of linguistics and put them into a computer. Now we’re starting to be able to do that,” says Goodman.
“It will take years of work but the dream is of a computer that really is thinking about what you want and what you mean rather than just what you said,” adds Frank.