{"pk":26956,"title":"Assessing the Linguistic Productivity of Unsupervised Deep Neural Networks","subtitle":null,"abstract":"Increasingly, cognitive scientists have demonstrated interest inapplying tools from deep learning. One use for deep learning isin language acquisition where it is useful to know if a linguisticphenomenon can be learned through domain-general means.To assess whether unsupervised deep learning is appropriate,we first pose a smaller question: Can unsupervised neural net-works apply linguistic rules productively, using them in novelsituations? We draw from the literature on determiner/nounproductivity by training an unsupervised, autoencoder networkmeasuring its ability to combine nouns with determiners. Oursimple autoencoder creates combinations it has not previouslyencountered and produces a degree of overlap matching adults.While this preliminary work does not provide conclusive evi-dence for productivity, it warrants further investigation withmore complex models. Further, this work helps lay the foun-dations for future collaboration between the deep learning andcognitive science communities.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[{"word":"Deep Learning; Language Acquisition; LinguisticProductivity; Unsupervised Learning; Determiners"}],"section":"Talks: Papers","is_remote":true,"remote_url":"https://escholarship.org/uc/item/72z2w2nd","frozenauthors":[{"first_name":"Lawrence","middle_name":"","last_name":"Phillips","name_suffix":"","institution":"Pacific Northwest National Laboratory","department":""},{"first_name":"Nathan","middle_name":"","last_name":"Hodas","name_suffix":"","institution":"Pacific Northwest National Laboratory","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2017-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/26956/galley/16592/download/"}]}