Word Learning as Category Formation

A fundamental question in word learning is how, given only evidence about what objects a word has previously referred to, children are able to generalize the total class (Smith, 1979; Xu and Tenenbaum, 2007). E.g. how a child ends up knowing that \textit{`poodle\u27} only picks out a specific subset of dogs rather than the whole class and vice versa. Here we present a computational model of word learning which accounts for a wide range of previously conflicting experimental findings