{"pk":32354,"title":"Building Lexical Representations Dynamically Using Artificial Neural Networks","subtitle":null,"abstract":"The topic of this paper is the development of dynamic lexical representations using artificial neural networks. In previous work on connectionist natural language processing a lot of approaches have experimented with manually encoded lexicon representations for words. However from a cognitive point of view as well as an engineering point of view it is difficult to find appropriate representations for the lexicon entries for a given task. In this context, this paper explores the use of building word representations during a training process for a particular task. Using simple recurrent networks, principal component analysis and hierarchical clustering we show how lexical representations can be formed dynamically, especially for neural network modules in large, real-world, computational speech-language modeIs.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Long Papers","is_remote":true,"remote_url":"https://escholarship.org/uc/item/2b8363cw","frozenauthors":[{"first_name":"Stefan","middle_name":"","last_name":"Wermter","name_suffix":"","institution":"Laboratoire de la Physiologie de la Perception et de l'Action, College de France/CNRS","department":""},{"first_name":"Manuela","middle_name":"","last_name":"Meurer","name_suffix":"","institution":"UCLA Psychology Department","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"1997-01-01T12:00:00-06:00","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/32354/galley/23419/download/"}]}