Paper: Fast Mapping in Word Learning: What Probabilities Tell Us

ACL ID W08-2108
Title Fast Mapping in Word Learning: What Probabilities Tell Us
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2008
Authors

Children can determine the meaning of a new word from hearing it used in a familiar context—an ability often referred to as fast mapping. In this paper, we study fast map- ping in the context of a general probabilistic model of word learning. We use our model to simulate fast mapping experiments on chil- dren, such as referent selection and retention. The word learning model can perform these tasks through an inductive interpretation of the acquired probabilities. Our results suggest that fast mapping occurs as a natural conse- quence of learning more words, and provides explanations for the (occasionally contradic- tory) child experimental data. 1 Fast Mapping An average six-year-old child knows over 14,000 words, most of which s/he has learned from hearing other people use them in ambi...