ICANN 1996: Artificial Neural Networks — ICANN 96 pp 275-280 | Cite as
Automatic Part-Of-Speech tagging of Thai corpus using neural networks
Abstract
A cost-effective method for Part-Of-Speech (POS) tagging of a Thai corpus using neural networks is proposed. Computer experiments show that this method has a success rate of over 80% for tagging text of untrained data, and an error rate below 8%. These results are much better than those obtained by conventional table lookup methods. Some experiments comparing original and various modified back-propagation algorithms for training the neural network tagger are also conducted. Results of these experiments show that the learning algorithm with DBDB adaptation rule at a semi-batch update mode is the best one for tagging text in terms of convergence rate and computaional complexity.
Keywords
Neural Network Target Word Natural Language Processing Machine Translation Neural Network MethodPreview
Unable to display preview. Download preview PDF.
References
- 1.Macleod, C., et al.: Developing multiply tagged corpora for lexical research, International Workshop on Directions of Lexical Research, Beijing, China, 1994.Google Scholar
- 2.Isahara, H., et al.: Development of tagged text database by real world computing partnership, First Annual Meeting of the Association for Natural Language Processing, Japan, 1995 (in Japanese).Google Scholar
- 3.Haykin, S. and Deng, C.: Classification of radar clutter using neural networks, IEEE Tran. on Neural Networks, Vol. 2, pp. 589–600, 1991.Google Scholar
- 4.Jacobs, R. A.: Increased rates of convergence through learning rate adaptation, Neural Networks, Vol. 1, pp. 295–307, 1988.Google Scholar
- 5.Ochiai, K., et al.: A new renewal rule of learning rate in neural networks, Transactions of Information Processing Society of Japan, pp. 1081–1090, 1984 (in Japanese).Google Scholar
- 6.Ochiai, K., et al.: Kick-out learning algorithm to reduce the oscillation of weights, Neural Networks, Vol. 7, pp. 797–807, 1994.Google Scholar
- 7.Haykin, S.: Neural Networks, Macmillan College Publishing Company, Inc., 1994.Google Scholar
- 8.Trantisawetrat, N. and Sirinaovakul, B.: An electronic dictionary for multilingual machine translation, Proceedings of the Symposim on Natural Language Processing in Thailand, pp. 377–411, 1993.Google Scholar