Phrase detection and the associative memory neural network

Author

Murphy, Richard C.

Author_Institution

Dept. of Comput. Sci. & Eng., Notre Dame Univ., USA

Volume

4

fYear

2003

fDate

20-24 July 2003

Firstpage

2599

Abstract

This paper describes the use of a novel associative memory neural network architecture to perform unsupervised phrase detection in a large, unstructured, English text corpus. To significantly increase the difficulty associated with processing the text corpus, the network is exposed to over 270 thousand Web pages from the .edu domain with no textual substitution or alteration (for spelling, grammar, etc.). The corpus, consisting of 150M words, is represented as a string of sparse tokens and phrase detection is performed through the use of the unique information theoretic quantity of mutual significance.

Keywords

content-addressable storage; information theory; neural net architecture; text analysis; .edu domain; Web pages; associative memory neural network architecture; information theory; large unstructured English text corpus; mutual significance; sparse token string; unsupervised phrase detection; Associative memory; Computer architecture; Computer science; Databases; Detectors; Humans; Memory architecture; Neural networks; Robustness; Web pages;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2003. Proceedings of the International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-7898-9

Type

conf

DOI

10.1109/IJCNN.2003.1223976

Filename

1223976