{"pk":28191,"title":"Modeling morphological affixation with interpretable recurrent networks: sequential rebinding controlled by hierarchical attention","subtitle":null,"abstract":"This paper proposes a recurrent neural network model thatlearns to perform morphological affixation, a fundamental op-eration of linguistic cognition, and has interpretable relationsto descriptions of morphology at the computational and algo-rithmic levels. The model represents morphological sequences(stems and affixes) with distributed representations that sup-port binding of symbols to ordinal positions and position-basedunbinding. Construction of an affixed form is controlled at theimplementation level by shifting attention between morphemesand across positions within each morpheme. The model suc-cessfully learns patterns of prefixation, suffixation, and infixa-tion, unifying these at all levels of description around the theo-retical notion of a pivot. Connections of the present proposal toneural coding of ordinal position, and to computational modelsof serial recall, are noted.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[{"word":"morphology; distributed representations; recur-rent networks; neural attention; multi-level descriptions"}],"section":"Publication-based-Talks","is_remote":true,"remote_url":"https://escholarship.org/uc/item/3wt1272g","frozenauthors":[{"first_name":"Colin","middle_name":"","last_name":"Wilson","name_suffix":"","institution":"John Hopkins","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2018-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/28191/galley/17850/download/"}]}