Learning in Wubble World

Why do children master language so quickly and thoroughly, whereas gigabytes of text and enormously sophisticated learning algorithms produce at best shallow semantics in machines? Because children have help from competent speakers who relate language to what\´s happening in the child\´s environment. To facilitate the task of machine word learning, we developed a simulated environment, called "Wubble World," and populated it with entities called wubbles. Children interact with the wubbles using natural language, and act as teachers when the wubble needs help. This paper presents our word learning algorithms and provides some empirical results.