Learning Word-to-meaning Mappings

Children face ve central diiculties when learning the vocabulary of their native language: learning from multi-word utterances, bootstrapping from an empty mental lexicon, referential uncertainty, noise, and homonymy. These diiculties are modeled formally via a simpliied lexical acquisition task called the mapping problem. Algorithms for solving this mapping problem are developed, based on the intuitive notions of cross-situational learning and the principle of contrast. Computer simulation demonstrates that these techniques are eeective in solving this mapping problem. This motivates the hypothesis that children use such techniques, inter alia, when learning language.