Title :
Towards classifying full-text using recurrent neural networks
Author :
Farkas, Jennifer
Author_Institution :
Centre for Infor. Tech. Innovation, Ind. Canada, Laval, Que., Canada
Abstract :
This paper describes an automatic document classification system called NeuroClass, developed for the air transportation field of Transport Canada. The properties of the system show that for the specific domain for which NeuroClass was developed, recurrent neural networks as developed by Elman (1990) can be used to build systems that classify natural language full-text automatically and reliably with a degree of accuracy proportional to the level of class adherence of the text involved
Keywords :
classification; full-text databases; natural languages; recurrent neural nets; NeuroClass; Transport Canada; accuracy; air transportation; automatic document classification system; class adherence; dictionary; full-text classification; natural language full-text; probability vector representation; recurrent neural networks; Artificial intelligence; Books; Dictionaries; Frequency conversion; Information technology; Out of order; Recurrent neural networks; Research and development; Technological innovation; Testing;
Conference_Titel :
Electrical and Computer Engineering, 1995. Canadian Conference on
Conference_Location :
Montreal, Que.
Print_ISBN :
0-7803-2766-7
DOI :
10.1109/CCECE.1995.528186
