Towards classifying full-text using recurrent neural networks

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.

[1]  Stefan Wermter.  Learning to Classify Natural Language Titles in a Recurrent Connectionist Model , 1991 .

[2]  W. Robertson,et al.  A neural algorithm for document clustering , 1991, Inf. Process. Manag..

[3]  J. Farkas,et al.  Generating document clusters using thesauri and neural networks , 1994, 1994 Proceedings of Canadian Conference on Electrical and Computer Engineering.

[4]  Jennifer Farkas.  Documents, concepts and neural networks , 1993, CASCON.

[5]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[6]  J. Farkas.  Neural networks and document classification , 1993, Proceedings of Canadian Conference on Electrical and Computer Engineering.

[7]  Gary Marchionini,et al.  A self-organizing semantic map for information retrieval , 1991, SIGIR '91.

[8]  Kui-Lam Kwok.  A neural network for probabilistic information retrieval , 1989, SIGIR '89.

[9]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[10]  Christian Jacquemin,et al.  A temporal connectionist approach to natural language , 1994, SGAR.

[11]  Vijay V. Raghavan,et al.  Automatic cluster assignment for documents , 1990, [1991] Proceedings. The Seventh IEEE Conference on Artificial Intelligence Application.