Why are verbs harder to learner than nouns? Initial insights from a computational model of situated word learning

Michael Fleischman, Deb Roy


We present a computational model that uses intention recognition as a basis for situated word learning. In an initial experiment, the model acquired a lexicon from situated natural language collected from human participants interacting in a virtual game environment. Similar to child language learning, the model learns nouns faster than verbs. In the model, this is due to inherent ambiguities in mapping verbs to inferred intentional structures. Since children must overcome similar ambiguities, the model provides a possible explanation for learning patterns in children.

Related Content