Modeling word perception using the Elman network

[摘要] This paper presents an automatic acquisition process to acquire the semantic meaning for the words. This process obtains the representation vectors for stemmed words by iteratively improving the vectors, using a trained Elman network. Experiments performed on a corpus composed of Shakespeare's writings show its linguistic analysis and categorization abilities. (C) 2008 Elsevier B.V. All rights reserved.

[发布日期] 2008-10-01

[效力级别]  Proceedings Paper

[关键词] Word perception;Compositional representation;Authorship;Stylistic similarity;Categorization;Semantic search;Elman network;Linguistic analysis;Personalized code;Content addressable memory;Polysemous word