Connectionist Approach to Generic Text Summarization
As the enormous amount of on-line text grows on the
World-Wide Web, the development of methods for automatically
summarizing this text becomes more important. The primary goal of
this research is to create an efficient tool that is able to summarize
large documents automatically. We propose an Evolving
connectionist System that is adaptive, incremental learning and
knowledge representation system that evolves its structure and
functionality. In this paper, we propose a novel approach for Part of
Speech disambiguation using a recurrent neural network, a paradigm
capable of dealing with sequential data. We observed that
connectionist approach to text summarization has a natural way of
learning grammatical structures through experience. Experimental
results show that our approach achieves acceptable performance.
[1] Amari, S., "A Theory of Adaptive Pattern Classifiers", IEEE Trans.,
Electron. Comput. 16:1143-1163.
[2] Amari, S. and Kasabov, N., "Brain-like Computing and Intelligent
Information System, Springer Verlag, Singapore.
[3] Arbib M, "The Handbook of Brain Theory and Neural Networks", MIT
Press, Cambridge, MA, (1995, 2002).
[4] Barak, A. Pearlmutter, "Gradient calculation for dynamic recurrent
neural networks: a survey", IEEE Transactions on Neural Networks,
6(5), pp. 1212-1228, 1995.
[5] Elman, Jeffrey L., "Distributed representations, Simple recurrent
networks, and grammatical Structure", Machine Learning, 7, pp. 195-
225.
[6] Freeman, W., "Neurodynamics", Springer, London, 2000.
[7] Garen Arevian, "Recurrent Neural Networks for Robust Real-World
Text Classification", IEEE/WIC/ACM International Conference on Web
Intelligence, 2007.
[8] Han, K.-H. And Kim, J.-H. "Quantum-inspired evolutionary algorithm
for a class of Combinational optimization", IEEE Transactions. Evol.
Comput., Vol. 6, No. 6, pp 580-593.
[9] Hebb, D., "The Organization of Behavior", Willey, New York.Haykin,
S., "Neural Networks: A Comprehensive Foundation", 2nd edition,
Prentice Hall, 1998.
[10] Hongyan Jing, "Sentence Reduction for Automatic Text
Summarization", Department of Computer Science Columbia University
New York, NY 10027, USA
[11] J. L. Elman, "Distributed representations, simple recurrent networks, and
grammatical structure," Machine Learning, vol. 7, pp. 195-225, 1991.
[12] Khosrow Kaikhah, "Text Summarization Using Neural Networks",
Faculty Publications-Comp. Science Texas State University,2004.
[13] Lei Yu1, Jia Ma1, Fuji Ren1, 2, Shingo Kuroiwa1, "Automatic Text
Summarization Based on Lexical Chains and Structural Features", ACIS,
Journal of Artificial Intelligence Research (1997), pp 574-578.
[14] Medsker, Larry R., "Hybrid Neural Network and Expert Systems",
Kluwer Academic Publishers.
[15] Mayberry,M. R. and Miikkulainen R., "Lexical Disambiguation on
Distributed Representations of Context Frequency", In Proceedings of
the 16th Annual Conference of the Cognitive Science Society (COGSCI-
94, Atlanta, GA), pp. 601-606.
[16] Nikola Kasabov, "Evolving Connectionist Systems", Springer, second
edition, 2007.
[17] Rosch, E. and Lloyd, "Cognition and Categorization", Lawrence
Erlbaum, Hillssale, NJ, 1978.
[18] Skapura, David M., "Building Neural Networks", ACM Press, New
York, pp.154-161.
[19] Smith, E.E. and Medin, D.L. "Categories and Concepts", Harward
University Press, Cambridge, MA, 1981.
[20] Stoianov, I. P., Nerbonne, J. and Bouma, H., "Modelling the Phonotactic
Structure of Natural Language Words with Simple Recurrent Networks",
Computational Linguistics in Netherlands 1997.
[21] Tebelskis, J., "Speech Recognition using Neural Networks", CMU-CS-
95-142, Carnegie Mellon University, Pittsburgh, PA, May 1995.
[22] Wermter, S., Weber V., "SCREEN: Learning a Flat Syntactic and
Semantic Spoken Language Analysis Using Artificial Neural Network",
pp. 35-85.
[23] William M. Ramsey, Stephen P. Stich, David E. Rumelhart, "Philosophy
and connectionist theory", Lawrence Erlbaum Associates, 1991,ISBN
0805805923, 9780805805925
[24] Yau-Hwang Kuo and Hsun-Hui Huang, "Automatic Extraction of Key
Sentences via Word Sense Identification for Chinese Text
Summarization", Journal of Advanced Computational Intelligence
Vol.11 No.4, 2007 and Intelligent Informatics.
[25] Taylor, J.G., "The Race for Consciousness", MIT Press, Cambridge,
MA., 1999.
[1] Amari, S., "A Theory of Adaptive Pattern Classifiers", IEEE Trans.,
Electron. Comput. 16:1143-1163.
[2] Amari, S. and Kasabov, N., "Brain-like Computing and Intelligent
Information System, Springer Verlag, Singapore.
[3] Arbib M, "The Handbook of Brain Theory and Neural Networks", MIT
Press, Cambridge, MA, (1995, 2002).
[4] Barak, A. Pearlmutter, "Gradient calculation for dynamic recurrent
neural networks: a survey", IEEE Transactions on Neural Networks,
6(5), pp. 1212-1228, 1995.
[5] Elman, Jeffrey L., "Distributed representations, Simple recurrent
networks, and grammatical Structure", Machine Learning, 7, pp. 195-
225.
[6] Freeman, W., "Neurodynamics", Springer, London, 2000.
[7] Garen Arevian, "Recurrent Neural Networks for Robust Real-World
Text Classification", IEEE/WIC/ACM International Conference on Web
Intelligence, 2007.
[8] Han, K.-H. And Kim, J.-H. "Quantum-inspired evolutionary algorithm
for a class of Combinational optimization", IEEE Transactions. Evol.
Comput., Vol. 6, No. 6, pp 580-593.
[9] Hebb, D., "The Organization of Behavior", Willey, New York.Haykin,
S., "Neural Networks: A Comprehensive Foundation", 2nd edition,
Prentice Hall, 1998.
[10] Hongyan Jing, "Sentence Reduction for Automatic Text
Summarization", Department of Computer Science Columbia University
New York, NY 10027, USA
[11] J. L. Elman, "Distributed representations, simple recurrent networks, and
grammatical structure," Machine Learning, vol. 7, pp. 195-225, 1991.
[12] Khosrow Kaikhah, "Text Summarization Using Neural Networks",
Faculty Publications-Comp. Science Texas State University,2004.
[13] Lei Yu1, Jia Ma1, Fuji Ren1, 2, Shingo Kuroiwa1, "Automatic Text
Summarization Based on Lexical Chains and Structural Features", ACIS,
Journal of Artificial Intelligence Research (1997), pp 574-578.
[14] Medsker, Larry R., "Hybrid Neural Network and Expert Systems",
Kluwer Academic Publishers.
[15] Mayberry,M. R. and Miikkulainen R., "Lexical Disambiguation on
Distributed Representations of Context Frequency", In Proceedings of
the 16th Annual Conference of the Cognitive Science Society (COGSCI-
94, Atlanta, GA), pp. 601-606.
[16] Nikola Kasabov, "Evolving Connectionist Systems", Springer, second
edition, 2007.
[17] Rosch, E. and Lloyd, "Cognition and Categorization", Lawrence
Erlbaum, Hillssale, NJ, 1978.
[18] Skapura, David M., "Building Neural Networks", ACM Press, New
York, pp.154-161.
[19] Smith, E.E. and Medin, D.L. "Categories and Concepts", Harward
University Press, Cambridge, MA, 1981.
[20] Stoianov, I. P., Nerbonne, J. and Bouma, H., "Modelling the Phonotactic
Structure of Natural Language Words with Simple Recurrent Networks",
Computational Linguistics in Netherlands 1997.
[21] Tebelskis, J., "Speech Recognition using Neural Networks", CMU-CS-
95-142, Carnegie Mellon University, Pittsburgh, PA, May 1995.
[22] Wermter, S., Weber V., "SCREEN: Learning a Flat Syntactic and
Semantic Spoken Language Analysis Using Artificial Neural Network",
pp. 35-85.
[23] William M. Ramsey, Stephen P. Stich, David E. Rumelhart, "Philosophy
and connectionist theory", Lawrence Erlbaum Associates, 1991,ISBN
0805805923, 9780805805925
[24] Yau-Hwang Kuo and Hsun-Hui Huang, "Automatic Extraction of Key
Sentences via Word Sense Identification for Chinese Text
Summarization", Journal of Advanced Computational Intelligence
Vol.11 No.4, 2007 and Intelligent Informatics.
[25] Taylor, J.G., "The Race for Consciousness", MIT Press, Cambridge,
MA., 1999.
@article{"International Journal of Information, Control and Computer Sciences:51128", author = "Rajesh S.Prasad and U. V. Kulkarni and Jayashree.R.Prasad", title = "Connectionist Approach to Generic Text Summarization", abstract = "As the enormous amount of on-line text grows on the
World-Wide Web, the development of methods for automatically
summarizing this text becomes more important. The primary goal of
this research is to create an efficient tool that is able to summarize
large documents automatically. We propose an Evolving
connectionist System that is adaptive, incremental learning and
knowledge representation system that evolves its structure and
functionality. In this paper, we propose a novel approach for Part of
Speech disambiguation using a recurrent neural network, a paradigm
capable of dealing with sequential data. We observed that
connectionist approach to text summarization has a natural way of
learning grammatical structures through experience. Experimental
results show that our approach achieves acceptable performance.", keywords = "Artificial Neural Networks (ANN); Computational
Intelligence (CI); Connectionist Text Summarizer ECTS (ECTS);
Evolving Connectionist systems; Evolving systems; Fuzzy systems
(FS); Part of Speech (POS) disambiguation.", volume = "3", number = "7", pages = "1694-5", }
