Distributed representation of word by using Elman network. (1st January 2013)

• Record Type: Journal Article
• Authors: Liou, Jiun-Wei; Cheng, Wei-Chen; Huang, Jau-Chi; Liou, Cheng-Yuan
• Is Part Of: International journal of intelligent information and database systems. Volume 7:Number 4(2013)
• Page Start: 373
• Page End: 386
• Publication Date: 2013-01-01
• Subjects: Elman network -- computational linguistics -- content addressable memory -- semantic indexing -- personalised codes -- neural network -- form-based similarity -- function-based similarity -- compositional representation -- intelligent system; Database management -- Computer programs -- Periodicals; Information retrieval -- Computer programs -- Periodicals; Information storage and retrieval systems -- Computer programs -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligent agents (Computer software) -- Periodicals; 006.33
• Languages: English
• ISSNs: 1751-5858

Abstract

This paper presents a novel training method for Elman network to encode the words in literary works. This network has been used in studying limited simple artificial sentences with varying degrees of success. This paper shows how to use it to process real-world works. Both word codes and network weights can be accomplished by the method. Each trained code is a distributed representation of its word. The training error can be drastically reduced by iteratively re-encoding the representations. Several distinct findings and results during the training process are reported.