{"pk":25649,"title":"Towards semantically rich and recursive word learning models","subtitle":null,"abstract":"Current models of word learning focus on the mapping between\nwords and their referents and remain mute with regard\nto conceptual representation. We develop a cross-situational\nmodel of word learning that captures word-concept mapping\nby jointly inferring the referents and underlying concepts for\neach word. We also develop a variant of our model that incorporates\nrecursion, which entertains the idea that children can\nuse learned words to aid future learning. We demonstrate both\nmodels’ ability to learn kinship terms and show that adding\nrecursion into the model speeds acquisition","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[{"word":"word learning; cross-situational learning; language\nacquisition"}],"section":"Papers","is_remote":true,"remote_url":"https://escholarship.org/uc/item/7mk082t2","frozenauthors":[{"first_name":"Francis","middle_name":"","last_name":"Mollica","name_suffix":"","institution":"University of Rochester","department":""},{"first_name":"Steven","middle_name":"T","last_name":"Piantadosi","name_suffix":"","institution":"University of Rochester","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2015-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/25649/galley/15273/download/"}]}